© 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. 7-RESID-POST-AA
    11. 81011
    Prev
    Next
    INDEX
    Explanations

    Dashes and special characters

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _typ
    -0.07
    stored
    -0.07
     composed
    -0.06
     endanger
    -0.06
     creditors
    -0.06
    (document
    -0.06
     conceivable
    -0.06
     Myanmar
    -0.06
    (download
    -0.06
    .highlight
    -0.06
    POSITIVE LOGITS
    .ua
    0.09
    enko
    0.08
     м
    0.07
    arResult
    0.07
    .ru
    0.07
    hev
    0.07
    меш
    0.07
     Sergey
    0.07
     сел
    0.07
    OV
    0.06
    Activations Density 1.143%

    No Known Activations