© 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. 28778
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical notation or symbols

    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
    layers
    -0.07
    ear
    -0.07
    ters
    -0.07
    Mic
    -0.07
    ways
    -0.06
    лим
    -0.06
    tera
    -0.06
    outs
    -0.06
    aren
    -0.06
    "default
    -0.06
    POSITIVE LOGITS
    atrix
    0.08
    chez
    0.08
    ¹
    0.07
     trÆ°ng
    0.07
    ipes
    0.07
    ulin
    0.07
    éĹ
    0.07
    AVING
    0.07
    skyt
    0.07
    ehen
    0.07
    Activations Density 0.045%

    No Known Activations