© 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. 42645
    Prev
    Next
    INDEX
    Explanations

    sentiment

    np_max-act · gemini-2.0-flash

    The neuron detects expressions of personal well-being, especially “feel” or “feeling” followed by positive descriptors like “better,” “good,” or 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
     눈을
    -0.07
    445
    -0.06
     datingside
    -0.06
     ()->
    -0.06
    мени
    -0.06
     relevance
    -0.06
    }/#{
    -0.06
     چند
    -0.06
     SearchResult
    -0.06
    戰
    -0.06
    POSITIVE LOGITS
    uisse
    0.07
    unca
    0.07
    enco
    0.07
     内
    0.06
     sme
    0.06
    sip
    0.06
    abis
    0.06
     vict
    0.06
     cabeza
    0.06
     halfway
    0.06
    Activations Density 0.015%

    No Known Activations