Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 127398
    Prev
    Next
    INDEX
    Explanations

    Drug/alcohol use, hallucinations

    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_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
     Presentation
    -0.07
    -corner
    -0.06
    RefCount
    -0.06
    ('{
    -0.06
    出品者
    -0.06
    การเล
    -0.06
    Mp
    -0.06
    ंगठन
    -0.06
    名無しさん
    -0.06
    instanc
    -0.06
    POSITIVE LOGITS
     вим
    0.07
     Celtics
    0.07
    ANDING
    0.07
    _drag
    0.07
     giấy
    0.06
    ्रव
    0.06
     nanny
    0.06
     özgür
    0.06
    EA
    0.06
    ,u
    0.06
    Activations Density 0.018%

    No Known Activations