© 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. 3-RESID-POST-AA
    11. 121667
    Prev
    Next
    INDEX
    Explanations

    .b

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ..↵↵
    -0.07
    38
    -0.07
    900
    -0.07
     весь
    -0.07
    週
    -0.07
     роз
    -0.07
    FLT
    -0.06
     Enum
    -0.06
     KD
    -0.06
     nonzero
    -0.06
    POSITIVE LOGITS
    Needs
    0.06
    blems
    0.06
    ulary
    0.06
    ์ล
    0.06
     neutr
    0.06
     pictured
    0.06
    desktop
    0.05
    翰
    0.05
     commissioned
    0.05
     천
    0.05
    Activations Density 0.095%

    No Known Activations