© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 84605
    Prev
    Next
    INDEX
    Explanations

    early disease research/treatment

    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
     відкрит
    -0.07
     kuş
    -0.07
    774
    -0.07
    notin
    -0.06
    равиль
    -0.06
    mime
    -0.06
    _current
    -0.06
    _Surface
    -0.06
    COMMAND
    -0.06
    _Result
    -0.06
    POSITIVE LOGITS
     palette
    0.07
     Quickly
    0.07
    DS
    0.07
     OnInit
    0.07
     الام
    0.06
     MI
    0.06
     Vital
    0.06
     UM
    0.06
    ูล
    0.06
     discard
    0.06
    Activations Density 0.042%

    No Known Activations