© 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. 60678
    Prev
    Next
    INDEX
    Explanations

    software or code

    np_max-act · gemini-2.0-flash

    mentions of upload-related components, APIs, or identifier names in technical/code text.

    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
    пеки
    -0.08
    ประโยชน
    -0.07
     aspect
    -0.07
     Arts
    -0.07
    ственное
    -0.06
     nouns
    -0.06
    기타
    -0.06
     objects
    -0.06
    Objects
    -0.06
     Sports
    -0.06
    POSITIVE LOGITS
    ER
    0.12
    er
    0.10
    aker
    0.10
    oner
    0.10
    poser
    0.09
    izers
    0.09
    HER
    0.09
    Runner
    0.09
    ers
    0.09
    izer
    0.09
    Activations Density 0.628%

    No Known Activations