© 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. 73559
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron fires on URL patterns in comment or license headers—i.e. things like “(http://…)” found in code comments.

    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
     Contin
    -0.06
    Contin
    -0.06
     Copp
    -0.06
    аліз
    -0.06
    211
    -0.06
     "'.$
    -0.06
     './
    -0.06
    _di
    -0.06
    =('
    -0.06
     Continuing
    -0.06
    POSITIVE LOGITS
    耐
    0.07
     escort
    0.07
     ambient
    0.07
    matchCondition
    0.07
    .onSubmit
    0.06
     sqlCommand
    0.06
    arch
    0.06
    .Focus
    0.06
    дат
    0.06
    .setDescription
    0.06
    Activations Density 0.008%

    No Known Activations