© 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. 128755
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving integrals

    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
    agas
    -0.08
    otti
    -0.08
    cob
    -0.08
     Geile
    -0.07
    uste
    -0.07
     sÃŃd
    -0.07
    /vendors
    -0.07
    isor
    -0.07
    uling
    -0.07
    HF
    -0.07
    POSITIVE LOGITS
    andon
    0.07
    aday
    0.07
    path
    0.07
    emann
    0.06
     Mane
    0.06
    _
    0.06
    ina
    0.06
    une
    0.06
     Fry
    0.06
    odes
    0.06
    Activations Density 0.054%

    No Known Activations