© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30591
    Prev
    Next
    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash

    The neuron fires on phrases expressing a judgment or evaluation—especially the “That sounds like a…” pattern.

    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
     was
    -0.07
    ени
    -0.07
    念
    -0.07
    			
↵			
↵
    -0.06
    ของร
    -0.06
     throws
    -0.06
     matching
    -0.06
     Moist
    -0.06
    _NOP
    -0.06
    Controller
    -0.06
    POSITIVE LOGITS
    .Txt
    0.07
    HQ
    0.06
     lexical
    0.06
    plementary
    0.06
    _Text
    0.06
    lust
    0.06
    (newState
    0.06
     Supplementary
    0.06
    _publish
    0.06
     Dispatch
    0.06
    Activations Density 0.032%

    No Known Activations