© 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. 83937
    Prev
    Next
    INDEX
    Explanations

    terms associated with definitive status and complicated narratives

    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
    onas
    -0.07
    zas
    -0.06
    iek
    -0.06
    IPA
    -0.06
     æ®
    -0.06
     Spo
    -0.06
    Neither
    -0.06
    ìĸ´
    -0.06
    opup
    -0.06
    ench
    -0.06
    POSITIVE LOGITS
     اÙĦرÙħزÙĬØ©
    0.09
     again
    0.07
    venient
    0.07
    виÑĩ
    0.07
    Symbol
    0.07
    again
    0.07
    Again
    0.07
    abin
    0.06
    alat
    0.06
    imest
    0.06
    Activations Density 0.000%

    No Known Activations