© 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. 105406
    Prev
    Next
    INDEX
    Explanations

    least

    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
     مح
    -0.07
    	tree
    -0.07
     sacred
    -0.06
    /INFO
    -0.06
     shaping
    -0.06
    校
    -0.06
    增长
    -0.06
     KH
    -0.06
     MW
    -0.06
     Nacht
    -0.06
    POSITIVE LOGITS
    _CHAT
    0.08
    'It
    0.06
    .erb
    0.06
    _does
    0.06
     spike
    0.06
    antry
    0.06
     frustrations
    0.06
    .Nil
    0.06
     complains
    0.06
    (assign
    0.06
    Activations Density 0.011%

    No Known Activations