© 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. 103602
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and timelines in historical 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
     hace
    -0.07
     recent
    -0.07
    ascimento
    -0.06
    ernen
    -0.06
    owie
    -0.06
    ãĥĭãĤ¢
    -0.06
    recent
    -0.06
     commons
    -0.06
    å¹³æĪIJ
    -0.06
    illion
    -0.06
    POSITIVE LOGITS
    oto
    0.07
    ilk
    0.07
    insk
    0.06
    isan
    0.06
    ém
    0.06
    oux
    0.06
    preneur
    0.06
     tongues
    0.06
    è¡Į
    0.06
     personally
    0.06
    Activations Density 0.023%

    No Known Activations