© 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. 42579
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron responds to code identifiers or tokens containing internal uppercase letters (e.g. CamelCase names).

    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
    apikey
    -0.07
    wipe
    -0.06
    :host
    -0.06
    ero
    -0.06
     XII
    -0.06
    زية
    -0.06
     onCreateView
    -0.06
    /topic
    -0.06
     OutlineInputBorder
    -0.06
     rooft
    -0.06
    POSITIVE LOGITS
     अज
    0.08
    +'/'+
    0.06
     thao
    0.06
     zombie
    0.06
    exclusive
    0.06
    ลล
    0.06
     Bloody
    0.06
     Kỳ
    0.06
     jdbcTemplate
    0.06
    Pont
    0.06
    Activations Density 0.205%

    No Known Activations