© 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. 20071
    Prev
    Next
    INDEX
    Explanations

    compress

    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
    Untitled
    -0.07
     thr
    -0.06
     Hakk
    -0.06
    (scope
    -0.06
    (nodes
    -0.06
    [offset
    -0.06
    (loop
    -0.06
    gender
    -0.06
     Blob
    -0.06
     Barcelona
    -0.06
    POSITIVE LOGITS
    maal
    0.07
    _CANNOT
    0.07
    یم
    0.07
     toàn
    0.07
    0.07
    /com
    0.07
    itler
    0.06
    .createObject
    0.06
     homeowner
    0.06
     Constructors
    0.06
    Activations Density 0.006%

    No Known Activations