© 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. 7-RESID-POST-AA
    11. 77330
    Prev
    Next
    INDEX
    Explanations

    One

    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
     gaz
    -0.07
     worse
    -0.06
    рон
    -0.06
     gam
    -0.06
     Böylece
    -0.06
    cept
    -0.06
     cue
    -0.06
     ort
    -0.06
    тери
    -0.06
    onaut
    -0.06
    POSITIVE LOGITS
    ,std
    0.07
    ','".$
    0.07
    ,key
    0.07
    ated
    0.06
     Booker
    0.06
    込み
    0.06
    =create
    0.06
    }/#{
    0.06
     अपन
    0.06
     instructor
    0.06
    Activations Density 0.000%

    No Known Activations