© 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. 113041
    Prev
    Next
    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash

    text fragments containing non-alphanumeric or non-ASCII symbols (e.g., currency signs, casting/operators, or templating/markup delimiters) within otherwise plain text.

    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
    ,temp
    -0.07
     vegas
    -0.06
     prosperity
    -0.06
    _suffix
    -0.06
    AVIS
    -0.06
    lymp
    -0.06
    _PROFILE
    -0.06
    irector
    -0.06
     sublist
    -0.06
     |[
    -0.06
    POSITIVE LOGITS
     wy
    0.07
     다른
    0.07
    Jun
    0.07
    /fast
    0.06
     junge
    0.06
     Ut
    0.06
     никогда
    0.06
    rement
    0.06
     Нас
    0.06
     IRA
    0.06
    Activations Density 1.467%

    No Known Activations