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. 81118
    Prev
    Next
    INDEX
    Explanations

    code

    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
     handling
    -0.07
    .block
    -0.07
     essays
    -0.07
     verg
    -0.06
    _colors
    -0.06
    positor
    -0.06
     sampled
    -0.06
     Overnight
    -0.06
     touched
    -0.06
    -photo
    -0.06
    POSITIVE LOGITS
     şöyle
    0.06
    _facebook
    0.06
    rh
    0.06
    .filtered
    0.06
    rov
    0.06
     svc
    0.06
     सव
    0.06
     سرم
    0.06
     haci
    0.06
    арат
    0.06
    Activations Density 0.034%

    No Known Activations