© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 66277
    Prev
    Next
    INDEX
    Explanations

    with in

    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
    (l
    -0.07
     church
    -0.07
    ΗΣ
    -0.07
    алом
    -0.07
    арч
    -0.07
    (p
    -0.07
    정을
    -0.06
     Leon
    -0.06
    -0.06
    (({
    -0.06
    POSITIVE LOGITS
    Suffix
    0.08
    Surname
    0.08
    _suffix
    0.08
    UFFIX
    0.07
     suffix
    0.07
     endings
    0.07
    .EndsWith
    0.07
    suffix
    0.07
     warfare
    0.07
     后
    0.07
    Activations Density 0.013%

    No Known Activations