© 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. 84167
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures and their contributions

    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
    uctive
    -0.07
     lately
    -0.07
    наÑĤ
    -0.06
    æľĢè¿ij
    -0.06
    agens
    -0.06
    оза
    -0.06
     Twice
    -0.06
    ovu
    -0.06
    orton
    -0.06
    erture
    -0.06
    POSITIVE LOGITS
     initially
    0.10
    æľĢåĪĿ
    0.09
     initial
    0.09
     inicial
    0.09
    initial
    0.09
     handful
    0.09
     modest
    0.09
    Initially
    0.09
     Initially
    0.09
    (initial
    0.08
    Activations Density 0.040%

    No Known Activations