© 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. 115488
    Prev
    Next
    INDEX
    Explanations

    Access, entry, ing

    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
     کارخانه
    -0.07
     九
    -0.06
    ิตย
    -0.06
    continued
    -0.06
    หย
    -0.06
    'l
    -0.06
    ์ก
    -0.06
     sonunda
    -0.06
    ีฟ
    -0.06
     Міністер
    -0.06
    POSITIVE LOGITS
     accessed
    0.10
     accessing
    0.09
     access
    0.08
     inaccessible
    0.08
    iov
    0.07
    ड़
    0.07
     accessible
    0.07
    Ax
    0.06
     accesses
    0.06
     ignored
    0.06
    Activations Density 0.017%

    No Known Activations