© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 103733
    Prev
    Next
    INDEX
    Explanations

    the

    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
     CY
    -0.07
    .variable
    -0.07
     segue
    -0.07
     Yoga
    -0.07
     máximo
    -0.07
    HASH
    -0.07
    TEMP
    -0.07
     MBA
    -0.07
    _units
    -0.07
    gaard
    -0.07
    POSITIVE LOGITS
     назива
    0.06
     Participants
    0.06
    ,↵
    0.06
     درمان
    0.06
     Panic
    0.06
    _Find
    0.06
     української
    0.05
    ी.
    0.05
     nond
    0.05
     raise
    0.05
    Activations Density 0.001%

    No Known Activations