© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 71117
    Prev
    Next
    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash

    punctuation and mathematical/code delimiters within formulas or technical text (operators, separators, and numeric punctuation).

    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
    络
    -0.07
    omm
    -0.07
    anteed
    -0.06
    WO
    -0.06
    نتی
    -0.06
    STE
    -0.06
     enumeration
    -0.06
    4
    -0.06
    writes
    -0.06
     covered
    -0.06
    POSITIVE LOGITS
    (hdc
    0.07
    /*.
    0.07
     lesbi
    0.07
     उ
    0.07
     tearDown
    0.06
    .Transform
    0.06
     hippoc
    0.06
    (Button
    0.06
     paraph
    0.06
     jobId
    0.06
    Activations Density 1.138%

    No Known Activations