© 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. 3-RESID-POST-AA
    11. 95432
    Prev
    Next
    INDEX
    Explanations

    TV

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -'.$
    -0.07
    bette
    -0.06
    束
    -0.06
     cree
    -0.06
    >>()
    -0.06
    .wh
    -0.06
    ColumnType
    -0.06
     Turnbull
    -0.06
     ή
    -0.06
    compet
    -0.06
    POSITIVE LOGITS
     TV
    0.13
     television
    0.11
    .tv
    0.09
     tv
    0.08
    TV
    0.08
     televised
    0.08
    Tv
    0.08
     Tv
    0.08
    tv
    0.07
    _TV
    0.07
    Activations Density 0.009%

    No Known Activations