© 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. 126648
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on speaker‐turn labels (the numeric IDs marking who’s speaking).

    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
     ridiculous
    -0.06
    .Creator
    -0.06
     Володими
    -0.06
    ená
    -0.06
    ані
    -0.06
     dangerous
    -0.06
    орі
    -0.06
    	delta
    -0.06
     reck
    -0.06
    emaker
    -0.06
    POSITIVE LOGITS
     Bronze
    0.07
     entrepreneurial
    0.07
    '));↵↵
    0.07
    (tokens
    0.06
     ******************************************************************************/↵
    0.06
    !
↵
    0.06
    ायन
    0.06
     좋아
    0.06
    徐
    0.06
    .vo
    0.06
    Activations Density 0.025%

    No Known Activations