© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 127196
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istani
    -0.07
    قی
    -0.06
    quisa
    -0.06
    _phone
    -0.06
    _HAVE
    -0.06
     Ω
    -0.06
    yne
    -0.06
    Vars
    -0.06
     oversized
    -0.06
    _lines
    -0.06
    POSITIVE LOGITS
    sampling
    0.07
    [t
    0.06
    />↵
    0.06
     retrospect
    0.06
     unaffected
    0.06
     emit
    0.06
    报名
    0.06
    Ta
    0.06
     MUCH
    0.06
     textbooks
    0.06
    Activations Density 0.001%

    No Known Activations