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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 10764
    Prev
    Next
    INDEX
    Explanations

    collect

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    の
    -0.06
    net
    -0.06
     Mein
    -0.06
    عمل
    -0.06
    *x
    -0.06
     افزایش
    -0.06
    PageRoute
    -0.06
    )(_
    -0.06
    bbb
    -0.06
     Ад
    -0.06
    POSITIVE LOGITS
    979
    0.06
    üy
    0.06
    /private
    0.06
    _EXECUTE
    0.06
     yo
    0.06
     etti
    0.06
    .ST
    0.06
    redients
    0.06
     플레이
    0.06
     vandal
    0.06
    Activations Density 0.002%

    No Known Activations