© 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. 119426
    Prev
    Next
    INDEX
    Explanations

    complex discussions surrounding race and identity

    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
    isse
    -0.07
    illis
    -0.07
    vore
    -0.07
    اا
    -0.07
    portfolio
    -0.07
    agenda
    -0.07
    ziel
    -0.07
    èŀį
    -0.06
     Darkness
    -0.06
    disposing
    -0.06
    POSITIVE LOGITS
     tong
    0.07
     spaces
    0.06
     trop
    0.06
     recom
    0.06
    çon
    0.06
    æħİ
    0.06
    /spec
    0.05
    azine
    0.05
     yet
    0.05
    uess
    0.05
    Activations Density 0.013%

    No Known Activations