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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45570
    Prev
    Next
    INDEX
    Explanations

    joint

    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
    artisanlib
    -0.07
    .Id
    -0.06
    ADIUS
    -0.06
    @(
    -0.06
     fate
    -0.06
     αδ
    -0.06
     ([
    -0.06
    (cat
    -0.06
     collateral
    -0.06
    -danger
    -0.06
    POSITIVE LOGITS
    ेकर
    0.07
     Mariners
    0.06
    ;,
    0.06
    hani
    0.06
     applauded
    0.06
    mouth
    0.06
    やって
    0.06
     notoriously
    0.06
    FACT
    0.06
    rops
    0.06
    Activations Density 0.010%

    No Known Activations