© 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. 653
    Prev
    Next
    INDEX
    Explanations

    identifiers start with letter

    np_max-act · gemini-2.0-flash

    This neuron activates on terms used in formal specifications of identifier or variable‐naming rules (e.g. letters, digits, underscores, beginnings, follows, 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
    marca
    -0.06
    structors
    -0.06
    .gstatic
    -0.06
    macı
    -0.06
    weetalert
    -0.06
     Himal
    -0.06
    >\
    -0.06
    racak
    -0.06
     gren
    -0.06
    (DEBUG
    -0.06
    POSITIVE LOGITS
    ace
    0.07
    	tx
    0.06
     Hor
    0.06
    ída
    0.06
    -CP
    0.06
    .setName
    0.06
     traceback
    0.06
    ordinator
    0.06
     cantidad
    0.06
    	Map
    0.06
    Activations Density 0.005%

    No Known Activations