© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 545
    Prev
    Next
    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash

    This neuron fires on formal mathematical-paper verbs that introduce or describe new results or methods—words like “prove,” “show,” “introduce,” “investigate,” and similar.

    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
     columnist
    -0.07
    他
    -0.07
    Sexy
    -0.06
                                                                  
    -0.06
     sesión
    -0.06
     Notifications
    -0.06
    .getServer
    -0.06
     paused
    -0.06
    riors
    -0.06
     Franti
    -0.06
    POSITIVE LOGITS
    conti
    0.07
     escre
    0.07
     ketogenic
    0.07
    ija
    0.06
     diren
    0.06
     missed
    0.06
    ::$_
    0.06
    >;↵
    0.06
    				       
    0.06
    _missing
    0.06
    Activations Density 0.044%

    No Known Activations