© 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. 15-RESID-POST-AA
    11. 36131
    Prev
    Next
    INDEX
    Explanations

    Quotations

    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
     potrav
    -0.06
    زية
    -0.06
     originate
    -0.06
     Enumerator
    -0.06
     Freem
    -0.06
    ́t
    -0.06
     Circus
    -0.06
    enterprise
    -0.06
    <|begin_of_text|>
    -0.06
     corps
    -0.05
    POSITIVE LOGITS
    .GetFiles
    0.07
    \param
    0.07
    .ReadAllText
    0.07
    .Cross
    0.07
    ext
    0.07
     *));↵
    0.06
    iqu
    0.06
     }↵↵↵
    0.06
     같다
    0.06
    erox
    0.06
    Activations Density 0.036%

    No Known Activations