© 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. 22-LLAMASCOPE-RES-131K
    11. 4325
    Prev
    Next
    INDEX
    Explanations

    key terms related to government policies and local businesses

    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
    says
    -0.09
     Says
    -0.08
     says
    -0.08
    ĥn
    -0.07
    itest
    -0.07
    ¯u
    -0.07
    kas
    -0.07
    ifu
    -0.07
     reportedly
    -0.06
    .Std
    -0.06
    POSITIVE LOGITS
     hadn
    0.14
     had
    0.13
     could
    0.11
     would
    0.10
     should
    0.10
    had
    0.10
     habÃŃa
    0.10
     shouldn
    0.09
     currently
    0.09
     hadde
    0.09
    Activations Density 0.096%

    No Known Activations