© 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. 19-RESID-POST-AA
    6. 52054
    Prev
    Next
    INDEX
    Explanations

    positive descriptions

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Luca
    -0.07
     Partition
    -0.07
     logistic
    -0.06
     deepen
    -0.06
     arterial
    -0.06
    正
    -0.06
    ulated
    -0.06
    assoc
    -0.06
     actionable
    -0.06
    株
    -0.06
    POSITIVE LOGITS
     kims
    0.06
    .Bot
    0.06
     nights
    0.06
    =event
    0.06
    _DISPLAY
    0.06
     강
    0.06
    _pemb
    0.06
     Nights
    0.06
     없
    0.06
     sağlay
    0.06
    Activations Density 0.146%

    No Known Activations