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. 42168
    Prev
    Next
    INDEX
    Explanations

    rugby

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “rugby,” especially in the phrases “rugby league” and “rugby union.”

    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
     CT
    -0.07
     fantas
    -0.07
    ANTLR
    -0.07
    .Cl
    -0.07
    UILabel
    -0.06
     购
    -0.06
     hak
    -0.06
    >::
    -0.06
    本当
    -0.06
     حرکت
    -0.06
    POSITIVE LOGITS
     rugby
    0.13
     Rugby
    0.11
     velmi
    0.08
    arhus
    0.07
     bardzo
    0.07
     zví
    0.07
     Rally
    0.07
    -rays
    0.06
    lige
    0.06
    odge
    0.06
    Activations Density 0.001%

    No Known Activations