© 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. 104869
    Prev
    Next
    INDEX
    Explanations

    code/technical language

    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
    ON
    -0.09
    on
    -0.08
     guessed
    -0.07
     motivations
    -0.07
     IDs
    -0.06
     on
    -0.06
    for
    -0.06
     On
    -0.06
     ion
    -0.06
    FOR
    -0.06
    POSITIVE LOGITS
    e
    0.17
     E
    0.15
    E
    0.15
    ke
    0.15
    le
    0.15
    .E
    0.15
     e
    0.15
    ne
    0.14
    NE
    0.14
    (e
    0.14
    Activations Density 1.182%

    No Known Activations