Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 10427
    Prev
    Next
    INDEX
    Explanations

    knew

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     回
    -0.07
    positor
    -0.07
    Per
    -0.07
     reporting
    -0.07
    -flag
    -0.06
    Remote
    -0.06
    Column
    -0.06
     Bernie
    -0.06
     gated
    -0.06
    ervation
    -0.06
    POSITIVE LOGITS
     yüz
    0.07
     плю
    0.07
     anch
    0.07
     cultivation
    0.06
    šk
    0.06
    [Boolean
    0.06
    [str
    0.06
     Kiev
    0.06
    udd
    0.06
     knows
    0.06
    Activations Density 0.022%

    No Known Activations