© 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 EvalsExportsAPI 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. 103809
    Prev
    Next
    INDEX
    Explanations

    down

    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
     erotic
    -0.08
     "::
    -0.07
    eti
    -0.07
    되지
    -0.07
    it
    -0.07
    Pří
    -0.07
     rif
    -0.07
     işaret
    -0.07
     çoğu
    -0.07
     吉
    -0.07
    POSITIVE LOGITS
     Down
    0.19
     down
    0.18
    Down
    0.16
     DOWN
    0.14
    down
    0.14
    .Down
    0.14
    -down
    0.13
    _DOWN
    0.13
    DOWN
    0.13
    .DOWN
    0.11
    Activations Density 0.042%

    No Known Activations