© 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. 902
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash

    This neuron primarily fires on tokens that mark the start of a character’s spoken first-person dialogue—especially the pronoun “I” in quotes.

    oai_token-act-pair · o4-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
    pub
    -0.07
    ندگان
    -0.06
     XVI
    -0.06
     mole
    -0.06
    速
    -0.06
     Mas
    -0.06
    ensible
    -0.06
    _eff
    -0.06
    -post
    -0.06
    Coll
    -0.06
    POSITIVE LOGITS
    (fs
    0.07
     tk
    0.07
    userinfo
    0.06
    (dateTime
    0.06
     ttk
    0.06
     NotImplementedError
    0.06
     حالة
    0.06
     teď
    0.06
     begun
    0.06
    arence
    0.06
    Activations Density 0.023%

    No Known Activations