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. 19-RESID-POST-AA
    6. 28645
    Prev
    Next
    INDEX
    Explanations

    Russian words

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dotenv
    -0.07
    /res
    -0.07
    Ky
    -0.07
    ิ
    -0.07
    .graph
    -0.07
     н
    -0.06
    ्पत
    -0.06
     adidas
    -0.06
    phones
    -0.06
    rush
    -0.06
    POSITIVE LOGITS
    atio
    0.07
     مالی
    0.06
     accr
    0.06
    -_
    0.06
     profitability
    0.06
     Greater
    0.06
    -м
    0.05
     μό
    0.05
    在线
    0.05
     attr
    0.05
    Activations Density 0.081%

    No Known Activations