© 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. 129658
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by clause-linking and transitional terms—especially the coordinating conjunction “or” and similar mid-sentence connectives like “depending,” “offline,” “use,” and “solvents.”

    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
    -three
    -0.07
     okolí
    -0.06
    —to
    -0.06
     reveals
    -0.06
    -transitional
    -0.06
     reveal
    -0.06
    ίων
    -0.06
    nock
    -0.06
     my
    -0.06
     Her
    -0.06
    POSITIVE LOGITS
     préc
    0.07
    ."
    ↵
    0.06
     ::↵
    0.06
    CHKERRQ
    0.06
    .patient
    0.06
    	logger
    0.06
    preced
    0.06
    >({
    0.06
    _nombre
    0.06
     NSArray
    0.06
    Activations Density 0.145%

    No Known Activations