© 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. 7826
    Prev
    Next
    INDEX
    Explanations

    file paths/modules

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that are parts of module or package import paths (i.e. segments in dotted or slash‐separated module 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
     Chore
    -0.07
     testimony
    -0.07
    427
    -0.07
     Мик
    -0.07
    Sand
    -0.07
     Honor
    -0.07
    ’я
    -0.07
     Preservation
    -0.06
    ../../
    -0.06
     Pix
    -0.06
    POSITIVE LOGITS
     splitter
    0.07
    uese
    0.06
    看
    0.06
     anyways
    0.06
    ategorie
    0.06
     Οικο
    0.06
     viel
    0.06
    EDURE
    0.06
    qualified
    0.06
     odak
    0.06
    Activations Density 0.020%

    No Known Activations