© 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. 41662
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the text is a block of programming code (e.g. code‐style tokens, syntax, imports, braces, etc.).

    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
    iveness
    -0.07
    -release
    -0.06
    armor
    -0.06
    ac
    -0.06
    ��이
    -0.06
    čné
    -0.06
     stellar
    -0.06
    .Car
    -0.06
     bree
    -0.06
    hum
    -0.06
    POSITIVE LOGITS
     Bash
    0.07
     Sinatra
    0.06
     whipped
    0.06
     Bool
    0.06
     LocalDate
    0.06
    .Mask
    0.06
    ("/
    0.06
    ρθρο
    0.06
    .match
    0.06
     yapılmış
    0.06
    Activations Density 0.005%

    No Known Activations