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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 72746
    Prev
    Next
    INDEX
    Explanations

    bracketed single quotes and periods

    np_max-act · gemini-2.0-flash

    data processing and manipulation tasks involving DataFrames in Python.

    oai_token-act-pair · gpt-4o-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
    (C
    -0.07
    .Marshal
    -0.06
    (Spring
    -0.06
    ainment
    -0.06
     的
    -0.06
    DRV
    -0.06
     transporter
    -0.06
    Cold
    -0.06
     Wol
    -0.06
     frankfurt
    -0.06
    POSITIVE LOGITS
    δα
    0.07
     når
    0.07
     în
    0.06
     [...]
    0.06
    пов
    0.06
     kişiler
    0.06
    _TAG
    0.06
    _RECV
    0.06
     Ramadan
    0.06
     vậy
    0.06
    Activations Density 0.006%

    No Known Activations