© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129784
    Prev
    Next
    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash

    This neuron never activates (all its outputs are zero), so it does not detect any pattern.

    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
    .getClassName
    -0.07
     LinearLayoutManager
    -0.07
     Lions
    -0.07
    азвание
    -0.06
     frontal
    -0.06
    _tem
    -0.06
    Poster
    -0.06
    sample
    -0.06
     notification
    -0.06
    -forward
    -0.06
    POSITIVE LOGITS
     مستق
    0.07
    GREE
    0.06
    Obsolete
    0.06
    Lf
    0.06
    zzarella
    0.06
     Swe
    0.06
    짓
    0.06
    	resp
    0.06
    <ll
    0.06
    ۲۰۲
    0.06
    Activations Density 0.039%

    No Known Activations