© 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. 15-RESID-POST-AA
    11. 35017
    Prev
    Next
    INDEX
    Explanations

    como

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;l
    -0.07
    ');?></
    -0.07
     Lew
    -0.07
     Append
    -0.06
     Pastor
    -0.06
     Dw
    -0.06
    δ
    -0.06
    865
    -0.06
     Energ
    -0.06
    10
    -0.06
    POSITIVE LOGITS
    amic
    0.08
     MA
    0.08
    _home
    0.08
    completion
    0.08
    -home
    0.08
    Although
    0.08
     commercial
    0.08
    με
    0.08
    كم
    0.07
    امه
    0.07
    Activations Density 0.030%

    No Known Activations