© 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. 61809
    Prev
    Next
    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash

    It detects interrogative utterances—tokens that mark questions (i.e., question punctuation/queries).

    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
     Bosch
    -0.06
    UIApplicationDelegate
    -0.06
    Numbers
    -0.06
     Kob
    -0.06
     Fulton
    -0.06
    IRTUAL
    -0.06
     nive
    -0.06
     arg
    -0.06
     Cush
    -0.06
     Cohen
    -0.06
    POSITIVE LOGITS
    .start
    0.07
     했다
    0.07
    ("(%
    0.07
    ĩa
    0.07
    ضوع
    0.07
     {:.
    0.07
    нак
    0.06
    (MethodImplOptions
    0.06
     jä
    0.06
    発表
    0.06
    Activations Density 0.091%

    No Known Activations