© 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. 91943
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron fires on the presence of embedded code snippets or programming‐style tokens (e.g. imports, function calls, backticks) indicating an included code example.

    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
     cla
    -0.06
    GORITHM
    -0.06
     cocktails
    -0.06
     Employee
    -0.06
     scho
    -0.06
     pod
    -0.06
     Tavern
    -0.06
     Edmonton
    -0.06
     advice
    -0.06
    .cap
    -0.06
    POSITIVE LOGITS
    _hdl
    0.07
     цел
    0.06
    hamster
    0.06
    執
    0.06
    しの
    0.06
    UpperCase
    0.06
    687
    0.06
    -member
    0.06
    _countries
    0.06
    Raster
    0.06
    Activations Density 0.043%

    No Known Activations