© 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. 18414
    Prev
    Next
    INDEX
    Explanations

    Programming code/discussion

    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
    rogen
    -0.06
    θεν
    -0.06
     sleeping
    -0.06
     Ke
    -0.06
     reception
    -0.06
     открыт
    -0.06
    .direction
    -0.06
    program
    -0.06
     Alger
    -0.06
     cultivated
    -0.06
    POSITIVE LOGITS
    **(
    0.07
    (l
    0.07
    <Base
    0.06
    _LEN
    0.06
    inidad
    0.06
     _("
    0.06
    \Url
    0.06
     timestamps
    0.06
    .getConfig
    0.06
    バ
    0.06
    Activations Density 0.094%

    No Known Activations