© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 44245
    Prev
    Next
    INDEX
    Explanations

    reading

    np_max-act · gemini-2.0-flash

    tokens that mark document structure or metadata (special header/end-of-text markers and related navigation/continuation links).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    around
    -0.07
     tile
    -0.06
    /var
    -0.06
     phức
    -0.06
    ูแล
    -0.06
     Survivor
    -0.06
     pared
    -0.06
    (layers
    -0.06
     tk
    -0.06
     ViewController
    -0.06
    POSITIVE LOGITS
    ")),
    0.07
     Case
    0.07
    झ
    0.07
    #",
    0.07
    .sign
    0.07
     uncert
    0.06
     sociedad
    0.06
    ドル
    0.06
    patches
    0.06
    >O
    0.06
    Activations Density 0.051%

    No Known Activations