© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 31571
    Prev
    Next
    INDEX
    Explanations

    Code/identifiers

    np_max-act · gemini-2.0-flash

    chat-format metadata and role/header tokens that mark system, user, or assistant sections in the transcript.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     лег
    -0.07
     sớm
    -0.07
     символ
    -0.07
    river
    -0.07
    थ
    -0.06
    argin
    -0.06
     predator
    -0.06
    _fps
    -0.06
     dân
    -0.06
    .Location
    -0.06
    POSITIVE LOGITS
    .Ab
    0.07
     Net
    0.07
     Initi
    0.06
     net
    0.06
     gross
    0.06
     puff
    0.06
    '][$
    0.06
    .disable
    0.06
     dfs
    0.06
    ustralian
    0.06
    Activations Density 1.060%

    No Known Activations