© 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. 11-RESID-POST-AA
    11. 26050
    Prev
    Next
    INDEX
    Explanations

    Bookings, fixes, hiring

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shock
    -0.08
    Blocks
    -0.06
     None
    -0.06
     reliably
    -0.06
    اک
    -0.06
     Davidson
    -0.06
     herein
    -0.06
    _ERR
    -0.06
    俺
    -0.06
     unarmed
    -0.06
    POSITIVE LOGITS
    ！」↵↵
    0.06
    ("");
↵
    0.06
    .Failure
    0.06
    щество
    0.06
    ADVERTISEMENT
    0.06
     práv
    0.06
    rán
    0.06
    "
↵
↵
    0.06
     measles
    0.06
    (Room
    0.06
    Activations Density 0.211%

    No Known Activations