© 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. 88984
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on mixed-case or uppercase identifier tokens—i.e. code symbols like class names, XML schema URLs, vendor/module names, and other CamelCase or all-caps tokens.

    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
     pom
    -0.07
    Rename
    -0.07
    Towards
    -0.06
     balk
    -0.06
     revisit
    -0.06
    AndPassword
    -0.06
    리
    -0.06
    bps
    -0.06
    inue
    -0.06
    _h
    -0.06
    POSITIVE LOGITS
    يرا
    0.06
     HttpHeaders
    0.06
    DG
    0.06
    IconModule
    0.06
    Camera
    0.06
     رابط
    0.06
     cloves
    0.06
     modest
    0.06
     인터
    0.06
    veyor
    0.05
    Activations Density 0.053%

    No Known Activations