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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 94232
    Prev
    Next
    INDEX
    Explanations

    played

    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
     Scientology
    -0.07
     hazards
    -0.07
     Haz
    -0.06
    _math
    -0.06
    .location
    -0.06
     افزار
    -0.06
    ItemSelected
    -0.06
     theology
    -0.06
    Skip
    -0.06
     fashion
    -0.06
    POSITIVE LOGITS
    :true
    0.07
    ofilm
    0.07
     mě
    0.07
     tb
    0.07
    Styled
    0.07
     vrouw
    0.06
     played
    0.06
    orgh
    0.06
    위
    0.06
    ..<
    0.06
    Activations Density 0.007%

    No Known Activations