© 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. 126207
    Prev
    Next
    INDEX
    Explanations

    specific dates and references to time

    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
    icense
    -0.07
     coco
    -0.07
    .alias
    -0.07
    еÑĢеÑĩ
    -0.06
    rips
    -0.06
    anel
    -0.06
    essional
    -0.06
     copp
    -0.06
    .GetObject
    -0.06
    .pag
    -0.06
    POSITIVE LOGITS
    ÙĪاء
    0.07
    orama
    0.07
    owy
    0.07
    oman
    0.06
    aling
    0.06
    aland
    0.06
     Pendant
    0.06
    clave
    0.06
    obs
    0.06
    apat
    0.06
    Activations Density 0.042%

    No Known Activations