© 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. 125935
    Prev
    Next
    INDEX
    Explanations

    medical studies

    np_max-act · gemini-2.0-flash

    This neuron detects descriptive qualifiers (adjectives or adverbs) that specify a condition’s stage, severity, or onset (e.g. “early,” “severely,” “primiparous,” “under”).

    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
     Rabbit
    -0.07
     Hansen
    -0.06
     componentDidMount
    -0.06
     Ambient
    -0.06
     Investigation
    -0.06
     Migration
    -0.06
    naissance
    -0.06
     Achievement
    -0.06
     Catalyst
    -0.06
    _content
    -0.06
    POSITIVE LOGITS
    ünkü
    0.07
    ;-
    0.07
     pourquoi
    0.06
    ."_
    0.06
    /k
    0.06
     achieves
    0.06
    :-
    0.06
    .'↵
    0.06
    multi
    0.06
     :",
    0.06
    Activations Density 0.092%

    No Known Activations