© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79628
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Uploaded
    -0.07
    _yaw
    -0.06
    ọn
    -0.06
     đạt
    -0.06
     można
    -0.06
     Бар
    -0.06
     Tur
    -0.06
    _fs
    -0.06
     Jelly
    -0.06
     werde
    -0.06
    POSITIVE LOGITS
     -----------------------------------------------------------------------------↵
    0.07
    Trademark
    0.07
     integral
    0.07
    looking
    0.06
    .Group
    0.06
     normalize
    0.06
     grand
    0.06
     --------------------
    0.06
     enlightenment
    0.06
     Cursor
    0.06
    Activations Density 0.001%

    No Known Activations