© 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. 73222
    Prev
    Next
    INDEX
    Explanations

    sameness

    np_max-act · gemini-2.0-flash

    It detects mentions of shared values, common interests, or community/belonging.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     немного
    -0.07
     hä
    -0.06
     cán
    -0.06
     требует
    -0.06
    给我
    -0.06
     rainbow
    -0.06
     cevap
    -0.06
     Licht
    -0.06
    �
    -0.06
     fucking
    -0.06
    POSITIVE LOGITS
    rganization
    0.07
    .BL
    0.06
    urred
    0.06
    ishment
    0.06
     Gen
    0.06
     &___
    0.06
     Fury
    0.06
     concepts
    0.06
    una
    0.06
     phenomena
    0.06
    Activations Density 0.025%

    No Known Activations