© 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. 11-RESID-POST-AA
    11. 36778
    Prev
    Next
    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash

    descriptions and details of physical characteristics and attributes of objects or beings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hassle
    -0.07
    .permissions
    -0.07
    AVED
    -0.06
    ematics
    -0.06
     Limit
    -0.06
     tents
    -0.06
    .direction
    -0.06
     sociology
    -0.06
     reaching
    -0.06
     масло
    -0.06
    POSITIVE LOGITS
     白
    0.07
     Springer
    0.07
    ohl
    0.07
     tts
    0.06
    *****/↵
    0.06
     brilliant
    0.06
     styled
    0.06
     Ball
    0.06
     Bord
    0.06
    berman
    0.06
    Activations Density 0.071%

    No Known Activations