© 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. 78173
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical features or changes in objects

    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
    æĹ¢
    -0.07
    pirit
    -0.06
    623
    -0.06
    ¨
    -0.06
    ĥn
    -0.06
    rin
    -0.06
    586
    -0.06
    science
    -0.06
    ates
    -0.05
     hereby
    -0.05
    POSITIVE LOGITS
     slightly
    0.10
     fewer
    0.09
     absence
    0.08
    pler
    0.08
     differences
    0.08
     difference
    0.08
     Differences
    0.07
    difference
    0.07
     instead
    0.07
    instead
    0.07
    Activations Density 0.028%

    No Known Activations