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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 114644
    Prev
    Next
    INDEX
    Explanations

    progress

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maternal
    -0.07
     baby
    -0.07
     lexical
    -0.07
    .findall
    -0.07
    interpret
    -0.07
     zone
    -0.07
    _AST
    -0.07
     Shirt
    -0.06
    MU
    -0.06
    charm
    -0.06
    POSITIVE LOGITS
     Wonder
    0.06
     Komment
    0.06
     Володими
    0.06
    »↵
    0.06
    ॰
    0.06
    udp
    0.06
    (false
    0.06
    人の
    0.06
    ıyorum
    0.06
    団
    0.06
    Activations Density 0.004%

    No Known Activations