© 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. 23-RESID-POST-AA
    11. 7674
    Prev
    Next
    INDEX
    Explanations

    alg

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entrepreneur
    -0.07
     pencils
    -0.07
     Vern
    -0.07
     decorating
    -0.06
     Merr
    -0.06
     Satellite
    -0.06
     Barker
    -0.06
     Sheikh
    -0.06
    avery
    -0.06
     Sullivan
    -0.06
    POSITIVE LOGITS
    agg
    0.07
    ukt
    0.07
     різних
    0.07
    song
    0.06
    /pp
    0.06
    umm
    0.06
    _HC
    0.06
    wald
    0.06
     раск
    0.06
     �
    0.06
    Activations Density 0.023%

    No Known Activations