© 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. 15-LLAMASCOPE-RES-131K
    11. 61715
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements associated with sports and physics

    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
    achuset
    -0.06
     Caribbean
    -0.06
     Jamaica
    -0.06
    é¾Ħ
    -0.05
     perme
    -0.05
     Sustainable
    -0.05
     Starter
    -0.05
    igator
    -0.05
     빨
    -0.05
     adjud
    -0.05
    POSITIVE LOGITS
    orque
    0.09
     spinning
    0.08
    -spin
    0.08
    _spin
    0.08
     spinner
    0.07
     spins
    0.07
    pole
    0.07
     Spinner
    0.07
    .spin
    0.07
    ãĥ³ãĥī
    0.07
    Activations Density 0.037%

    No Known Activations