© 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. 68306
    Prev
    Next
    INDEX
    Explanations

    inverse relationships

    np_max-act · gemini-2.0-flash

    terms associated with obesity and metabolic regulation.

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

    This neuron detects terminology of statistical correlations—especially phrases indicating an “inverse relationship” between two measured quantities.

    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
     repeatedly
    -0.08
    mae
    -0.06
    MMM
    -0.06
    Safety
    -0.06
    ับ
    -0.06
    ===
    -0.06
    割
    -0.06
    انه
    -0.06
    ambah
    -0.06
     searches
    -0.06
    POSITIVE LOGITS
    .getEmail
    0.07
    (tree
    0.06
    parseFloat
    0.06
    (lang
    0.06
    _lang
    0.06
     preorder
    0.06
    (EVENT
    0.06
     đặc
    0.06
    _svc
    0.06
    ?id
    0.06
    Activations Density 0.009%

    No Known Activations