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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 81260
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    the presence of placeholder tokens for person names (e.g. NAME_#) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to early prominent figures in psychology.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     Ice
    -0.06
    _processing
    -0.06
    達
    -0.06
    worm
    -0.06
    usuarios
    -0.06
    Bell
    -0.06
    _patterns
    -0.06
    OW
    -0.06
     referencing
    -0.06
    862
    -0.06
    POSITIVE LOGITS
     activating
    0.07
     Tencent
    0.07
    .getItemId
    0.06
    报名
    0.06
     Samsung
    0.06
    官方
    0.06
    \Schema
    0.06
     into
    0.06
     splits
    0.06
     PVC
    0.06
    Activations Density 0.204%

    No Known Activations