© 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. 89739
    Prev
    Next
    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash

    This neuron detects references to importing or excluding pages, assemblies, or solutions from another project or solution.

    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
    .Angle
    -0.07
     bel
    -0.07
    -left
    -0.06
    PAIR
    -0.06
     scheme
    -0.06
     specific
    -0.06
     Robbins
    -0.06
     long
    -0.06
    It
    -0.06
     Order
    -0.06
    POSITIVE LOGITS
    icipant
    0.07
    _tc
    0.07
     quotid
    0.06
     dood
    0.06
     ic
    0.06
     гро
    0.06
     Devin
    0.06
     vids
    0.06
     Quadr
    0.06
    털
    0.06
    Activations Density 0.056%

    No Known Activations