© 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. 125230
    Prev
    Next
    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash

    This neuron flags the capitalized identifier tokens (class or file names and acronyms) in code‐file headers.

    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
    _ma
    -0.06
    (assigns
    -0.06
    hasMany
    -0.06
    ーリ
    -0.06
    Choice
    -0.06
    طار
    -0.06
     \''
    -0.06
     lobster
    -0.06
     litre
    -0.06
     staveb
    -0.06
    POSITIVE LOGITS
     Employ
    0.06
     było
    0.06
     minimise
    0.06
    ournée
    0.06
     Normalize
    0.06
     MULTI
    0.06
     initials
    0.06
     Giles
    0.06
     Làm
    0.06
     Faculty
    0.06
    Activations Density 0.003%

    No Known Activations