© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 87387
    Prev
    Next
    INDEX
    Explanations

    :

    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
    racak
    -0.06
     Sacred
    -0.06
     Commons
    -0.06
     Throughout
    -0.06
    _section
    -0.06
    Currency
    -0.06
     hiểm
    -0.06
     Examples
    -0.06
    bold
    -0.06
    [MAX
    -0.06
    POSITIVE LOGITS
    습
    0.07
    oron
    0.07
     Toe
    0.07
    icrobial
    0.07
    [len
    0.06
     поперед
    0.06
     nær
    0.06
    ographs
    0.06
    .Logic
    0.06
    esor
    0.06
    Activations Density 0.006%

    No Known Activations