© 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. 77553
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or functions

    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
    .
    -0.07
    ’
    -0.07
    .↵
    -0.06
    ´
    -0.06
    --↵
    -0.06
    Ê
    -0.06
    `
    -0.06
    &apos
    -0.06
    &
    -0.06
     o
    -0.06
    POSITIVE LOGITS
     â
    0.13
     Ãİ
    0.11
    ÃħŸ
    0.09
    âb
    0.09
    Ãİ
    0.09
    ÃĦŸ
    0.09
     kâ
    0.09
    ân
    0.08
    âm
    0.08
    âk
    0.08
    Activations Density 0.044%

    No Known Activations