Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 104857
    Prev
    Next
    INDEX
    Explanations

    available

    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
    .slug
    -0.07
     Σχ
    -0.07
    -fields
    -0.07
     최근
    -0.06
    oned
    -0.06
    resolver
    -0.06
    ossier
    -0.06
     burgl
    -0.06
     cubes
    -0.06
    Markup
    -0.06
    POSITIVE LOGITS
    ucz
    0.07
     Available
    0.07
    oby
    0.07
    bec
    0.07
     albeit
    0.07
     مست
    0.06
    xAC
    0.06
     available
    0.06
    oper
    0.06
    ช
    0.06
    Activations Density 0.003%

    No Known Activations