© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 130231
    Prev
    Next
    INDEX
    Explanations

    uncertainty and explanations

    np_max-act · gemini-2.0-flash

    documentation-style phrases that describe how to handle cases via configurable options/methods, including defaults and conflict resolution.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    Click
    -0.07
    운데
    -0.07
    icie
    -0.07
     stir
    -0.06
    ccb
    -0.06
     viele
    -0.06
    gray
    -0.06
     frm
    -0.06
    幸
    -0.06
     چیزی
    -0.06
    POSITIVE LOGITS
    Panel
    0.07
     resultSet
    0.06
    рования
    0.06
     jug
    0.06
     stopwatch
    0.06
    .Project
    0.06
     "<
    0.06
     Tuple
    0.06
    enario
    0.06
     Printed
    0.06
    Activations Density 0.225%

    No Known Activations