© 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. 42312
    Prev
    Next
    INDEX
    Explanations

    .h

    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
    라는
    -0.07
    acock
    -0.07
    ьому
    -0.06
    TOCOL
    -0.06
     церков
    -0.06
     âm
    -0.06
     assoc
    -0.06
     beiden
    -0.06
     спроб
    -0.06
     економ
    -0.06
    POSITIVE LOGITS
     StringBuffer
    0.07
    ()*
    0.06
    \x
    0.06
    /log
    0.06
    "';↵
    0.06
     respecting
    0.06
    \s
    0.06
    _valor
    0.06
    branches
    0.06
    <dim
    0.06
    Activations Density 0.001%

    No Known Activations