© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3958
    Prev
    Next
    INDEX
    Explanations

    references to lace making and its associated elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isser
    -0.07
     foreign
    -0.07
    ÐĬ
    -0.07
    batch
    -0.07
    Batch
    -0.07
     batch
    -0.06
    emin
    -0.06
    åı°
    -0.06
    elsea
    -0.06
    ucc
    -0.06
    POSITIVE LOGITS
     village
    0.08
    patterns
    0.07
     villages
    0.07
     patterns
    0.07
     Vill
    0.07
     Sellers
    0.06
    'gc
    0.06
     villagers
    0.06
     trap
    0.06
    æĻ´
    0.06
    Activations Density 0.004%

    No Known Activations