© 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. 49879
    Prev
    Next
    INDEX
    Explanations

    Article/blog snippets

    np_max-act · gemini-2.0-flash

    discussions about social movements and advocacy relating to marginalized groups.

    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
     Gam
    -0.07
     bran
    -0.06
     другой
    -0.06
    74
    -0.06
     Мар
    -0.06
    ']),
    -0.06
     discussion
    -0.06
     altri
    -0.06
     humans
    -0.06
    кой
    -0.06
    POSITIVE LOGITS
    &W
    0.07
     LN
    0.07
    větší
    0.07
     Trotsky
    0.07
     břez
    0.07
    ریق
    0.06
     पक
    0.06
     Marco
    0.06
     infiltr
    0.06
    Johnny
    0.06
    Activations Density 0.249%

    No Known Activations