© 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. 7641
    Prev
    Next
    INDEX
    Explanations

    Talking or not talking

    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
     sud
    -0.07
    -vesm
    -0.07
     Vě
    -0.07
    ема
    -0.07
     Uma
    -0.07
     Px
    -0.06
    equality
    -0.06
     ev
    -0.06
     То
    -0.06
     Sou
    -0.06
    POSITIVE LOGITS
    taş
    0.07
     everlasting
    0.06
    hotmail
    0.06
     квіт
    0.06
    (vars
    0.06
     Millionen
    0.06
    /preferences
    0.06
    using
    0.06
    logout
    0.06
    п
    0.06
    Activations Density 0.027%

    No Known Activations