© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    terms related to software features and their compatibility

    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
    Äı
    -0.07
    ắn
    -0.07
    linger
    -0.06
     somehow
    -0.06
    sgi
    -0.06
     nickel
    -0.06
    мом
    -0.06
    RIGHT
    -0.06
    Ngh
    -0.06
    .appspot
    -0.06
    POSITIVE LOGITS
     future
    0.09
     next
    0.09
     soon
    0.09
    (next
    0.08
    future
    0.08
    æľªæĿ¥
    0.07
    uture
    0.07
     próxima
    0.07
    .Future
    0.07
     sooner
    0.07
    Activations Density 0.014%

    No Known Activations