© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 51756
    Prev
    Next
    INDEX
    Explanations

    immigration

    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
     عل
    -0.07
     праці
    -0.06
    .Slice
    -0.06
     rejection
    -0.06
     prendre
    -0.06
     tails
    -0.06
    ouble
    -0.06
     municipality
    -0.06
     jih
    -0.06
     OSD
    -0.06
    POSITIVE LOGITS
    >').
    0.08
     murderer
    0.07
    =session
    0.07
    ！
    0.07
    plugins
    0.06
    _(
    0.06
    (entries
    0.06
    �
    0.06
    [i
    0.06
    ansom
    0.06
    Activations Density 0.016%

    No Known Activations