© 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. 40785
    Prev
    Next
    INDEX
    Explanations

    Caching

    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
     hung
    -0.07
    vero
    -0.07
     села
    -0.07
    IMATE
    -0.07
    YP
    -0.07
     fortunes
    -0.06
    Jun
    -0.06
    polation
    -0.06
     incapable
    -0.06
    ches
    -0.06
    POSITIVE LOGITS
    _disk
    0.07
     tarn
    0.06
     Override
    0.06
    урс
    0.06
     LET
    0.06
     ResponseEntity
    0.06
    .nav
    0.06
     buộc
    0.06
     maybe
    0.06
     fertility
    0.06
    Activations Density 0.039%

    No Known Activations