© 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. 120937
    Prev
    Next
    INDEX
    Explanations

    swapping or reversing

    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
     Profession
    -0.06
    Git
    -0.06
    draw
    -0.06
     racing
    -0.06
     habitats
    -0.06
    NoSuch
    -0.06
    “(
    -0.06
    Arm
    -0.06
    Mid
    -0.06
    _bt
    -0.06
    POSITIVE LOGITS
    _CHANGE
    0.07
    (addr
    0.06
     
    0.06
    駅徒歩
    0.06
     Posts
    0.06
    .populate
    0.06
    �
    0.06
     player
    0.06
    _NEW
    0.06
    _MEM
    0.06
    Activations Density 0.018%

    No Known Activations