© 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. 15-RESID-POST-AA
    11. 56682
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    mentions of harm, danger, or spreading damaging effects to people, property, or the surrounding area.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一步
    -0.06
     -$
    -0.06
    (schema
    -0.06
    TextBox
    -0.06
     peasants
    -0.06
    $where
    -0.06
    .Uri
    -0.06
    glomer
    -0.06
    &&
    -0.06
    $s
    -0.06
    POSITIVE LOGITS
     rele
    0.07
    recover
    0.07
    asset
    0.07
     Vale
    0.06
     pre
    0.06
    			
↵			
↵
    0.06
    SUM
    0.06
     chemistry
    0.06
     mã
    0.06
     Poor
    0.06
    Activations Density 0.054%

    No Known Activations