© 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. 128623
    Prev
    Next
    INDEX
    Explanations

    Varied situations/feelings

    np_max-act · gemini-2.0-flash

    This neuron detects words expressing frustration or boredom (negative affect terms like “bored,” “frustrated,” etc.).

    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
     today
    -0.06
    disposed
    -0.06
    rodu
    -0.06
    eldorf
    -0.06
    وه
    -0.06
     Nou
    -0.06
    299
    -0.06
    :::::::::::::::
    -0.06
    .idea
    -0.06
    ￣￣￣
    -0.06
    POSITIVE LOGITS
     ¬
    0.07
     mücadel
    0.06
     minWidth
    0.06
     navCtrl
    0.06
    .createTextNode
    0.06
     Clemson
    0.06
    .fromString
    0.06
    ">(
    0.06
     Super
    0.06
     elabor
    0.06
    Activations Density 0.152%

    No Known Activations