© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108830
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash

    associations between specific biomarkers and cancer risk.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects statistical effect‐size and confidence‐interval reporting (e.g. pooled odds ratios, risk ratios, CIs, and related meta‐analysis metrics).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ------------------------------------------------
    -0.06
    wi
    -0.06
    .{
    -0.06
    elter
    -0.06
     WAS
    -0.06
    Recorder
    -0.06
    .Pattern
    -0.06
     ****************************************************************
    -0.06
    _pres
    -0.06
    ี้↵
    -0.05
    POSITIVE LOGITS
     mềm
    0.07
    hamster
    0.07
     Bundy
    0.07
     glanced
    0.07
     typu
    0.06
     snug
    0.06
     출력
    0.06
     trái
    0.06
     باعث
    0.06
    ("="
    0.06
    Activations Density 0.018%

    No Known Activations