© 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. 103930
    Prev
    Next
    INDEX
    Explanations

    bits

    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
    ्ब
    -0.07
    -cr
    -0.07
    APolynomial
    -0.07
    }↵↵↵↵↵↵
    -0.07
    yte
    -0.07
    _evt
    -0.07
    utting
    -0.07
    かって
    -0.07
    оны
    -0.07
    OSE
    -0.06
    POSITIVE LOGITS
     �
    0.07
     env
    0.07
     tags
    0.06
    :none
    0.06
    чів
    0.06
    (components
    0.06
    '"
    0.06
    ,length
    0.05
    Î
    0.05
    .weixin
    0.05
    Activations Density 0.018%

    No Known Activations