© 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. 78769
    Prev
    Next
    INDEX
    Explanations

    business names or organizational identifiers in various contexts

    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
    oles
    -0.08
    oir
    -0.08
    Traits
    -0.07
    ould
    -0.07
    uxe
    -0.07
     gord
    -0.07
    endo
    -0.07
     Bers
    -0.07
    orm
    -0.06
     Warriors
    -0.06
    POSITIVE LOGITS
     we
    0.12
    ï¼ĮæĪij们
    0.10
     there
    0.09
    æĪij们
    0.08
     ìļ°ë¦¬ëĬĶ
    0.08
     you
    0.08
    æĪijåĢij
    0.07
     мÑĭ
    0.07
     they
    0.07
    attern
    0.07
    Activations Density 0.007%

    No Known Activations