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. 28530
    Prev
    Next
    INDEX
    Explanations

    claims

    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
     preset
    -0.08
    	and
    -0.08
    bench
    -0.07
    すす
    -0.06
    -now
    -0.06
     Inst
    -0.06
     Comparative
    -0.06
     grounding
    -0.06
     Mass
    -0.06
    }-${
    -0.06
    POSITIVE LOGITS
    =name
    0.07
    .fixed
    0.07
    -Line
    0.07
    alli
    0.06
    _CLOSED
    0.06
    onec
    0.06
     пласти
    0.06
    (scanner
    0.06
     salesman
    0.06
    ắc
    0.06
    Activations Density 0.006%

    No Known Activations