© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73696
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash

    This neuron activates strongly on long code identifiers (class, function, or constant names) typically written in CamelCase or snake_case.

    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
     iT
    -0.06
    >c
    -0.06
     Attacks
    -0.06
     demand
    -0.06
    demand
    -0.06
    pherd
    -0.06
     Wer
    -0.06
    ade
    -0.06
     festivals
    -0.06
    Demand
    -0.06
    POSITIVE LOGITS
    لام
    0.08
    Intersection
    0.07
     QString
    0.07
    ião
    0.07
    ocity
    0.07
     CharSequence
    0.07
    ości
    0.07
     статус
    0.06
     đào
    0.06
     downloads
    0.06
    Activations Density 0.069%

    No Known Activations