© 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. 89580
    Prev
    Next
    INDEX
    Explanations

    sitting on

    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
    地下
    -0.08
     join
    -0.07
    .buy
    -0.07
     paginate
    -0.07
     Mp
    -0.07
     electr
    -0.07
     Despite
    -0.07
    ène
    -0.06
     observ
    -0.06
     SAC
    -0.06
    POSITIVE LOGITS
    [label
    0.07
     OnInit
    0.07
     státní
    0.06
     housing
    0.06
     safeg
    0.06
    ord
    0.06
     razor
    0.06
    flutter
    0.06
    -helper
    0.06
     zł
    0.06
    Activations Density 0.049%

    No Known Activations