© 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. 73557
    Prev
    Next
    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of something being done or proposed “first,” i.e. it detects the word “first” marking an initial occurrence or introduction.

    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
     dlg
    -0.06
     segments
    -0.06
    Semaphore
    -0.06
    compile
    -0.06
     slav
    -0.06
     segment
    -0.06
    dyn
    -0.06
    PAL
    -0.06
    :P
    -0.06
    /modal
    -0.06
    POSITIVE LOGITS
     Powered
    0.06
    enské
    0.06
    ']},↵
    0.06
     authDomain
    0.06
     fictional
    0.06
    uncios
    0.06
    .Collapsed
    0.06
     hük
    0.06
     editors
    0.06
     okres
    0.06
    Activations Density 0.030%

    No Known Activations