Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8312
    Prev
    Next
    INDEX
    Explanations

    distances and measurements

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical measurements of separation or clearance (e.g., “18 inches of separation between electrical and data lines”).

    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
     обра
    -0.07
     closes
    -0.06
     matcher
    -0.06
    HDR
    -0.06
     Putting
    -0.06
    _THE
    -0.06
     Spotlight
    -0.06
    蕉
    -0.06
    edef
    -0.06
     TU
    -0.06
    POSITIVE LOGITS
    StatusLabel
    0.06
    ButtonClick
    0.06
     Plains
    0.06
     Estados
    0.06
     jMenuItem
    0.06
    香
    0.06
    _dp
    0.06
    임
    0.06
     Minecraft
    0.06
    Outlined
    0.06
    Activations Density 0.010%

    No Known Activations