© 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. 74656
    Prev
    Next
    INDEX
    Explanations

    positive evaluations and anticipatory language related to musical performances and bands

    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
    kie
    -0.07
    icus
    -0.07
    ustr
    -0.07
    efe
    -0.07
     ná»ķi
    -0.06
    ĨĴ
    -0.06
    997
    -0.06
    bersome
    -0.06
    ogra
    -0.06
    æ¹
    -0.06
    POSITIVE LOGITS
     future
    0.14
    future
    0.12
     hopefully
    0.10
     futuro
    0.10
     Future
    0.09
     бÑĥдÑĥÑī
    0.09
    æľªæĿ¥
    0.09
     definitely
    0.09
     Hopefully
    0.09
    Future
    0.09
    Activations Density 0.055%

    No Known Activations