© 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. 15-RESID-POST-AA
    11. 28247
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    instances of chat/document meta markers and role/header tokens (conversation formatting and metadata).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    ==========
    -0.07
    ült
    -0.07
    Mensaje
    -0.06
    chef
    -0.06
    ===========
    -0.06
     gist
    -0.06
    てる
    -0.06
     된
    -0.06
     füh
    -0.06
    rends
    -0.06
    POSITIVE LOGITS
     asoci
    0.07
     youre
    0.07
    =en
    0.07
     motorcycle
    0.07
     thậm
    0.07
     الإن
    0.06
    099
    0.06
     partnerships
    0.06
    _range
    0.06
    .ng
    0.06
    Activations Density 0.336%

    No Known Activations