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. 81350
    Prev
    Next
    INDEX
    Explanations

    mult

    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
    욕
    -0.07
    다
    -0.07
    _io
    -0.07
     Gas
    -0.06
     Paz
    -0.06
     تر
    -0.06
     Advantage
    -0.06
    _target
    -0.06
    hydr
    -0.06
    ourcem
    -0.06
    POSITIVE LOGITS
    活动
    0.07
    SY
    0.07
    -vars
    0.07
    qu
    0.07
    ,const
    0.06
    acies
    0.06
    .intersection
    0.06
    ?");↵
    0.06
     FormBuilder
    0.06
     DateTimeKind
    0.06
    Activations Density 0.005%

    No Known Activations