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

    Neuronpedia

    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. 7-RESID-POST-AA
    11. 41007
    Prev
    Next
    INDEX
    Explanations

    -

    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
    (glm
    -0.07
     цим
    -0.07
    래스
    -0.07
    POR
    -0.07
    RTL
    -0.07
     Bernardino
    -0.06
    _Key
    -0.06
     ctype
    -0.06
    ToString
    -0.06
    _bins
    -0.06
    POSITIVE LOGITS
    Reviewed
    0.06
     Duplicate
    0.06
    ”?
    0.06
    uations
    0.06
    Exc
    0.06
    }elseif
    0.06
     PS
    0.06
     junk
    0.06
     reduce
    0.06
    个
    0.06
    Activations Density 0.002%

    No Known Activations