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. 11-RESID-POST-AA
    6. 51116
    Prev
    Next
    INDEX
    Explanations

    record document

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _dn
    -0.07
     F
    -0.07
     *_
    -0.07
    Sys
    -0.06
    _TO
    -0.06
     ']
    -0.06
    iye
    -0.06
    करण
    -0.06
    Cmd
    -0.06
    TypeDef
    -0.06
    POSITIVE LOGITS
    ائم
    0.06
    accepted
    0.06
    Creative
    0.06
    -tra
    0.06
    delete
    0.06
     склад
    0.06
     wur
    0.06
    logger
    0.06
     öl
    0.06
    의
    0.06
    Activations Density 0.022%

    No Known Activations