© 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. 60780
    Prev
    Next
    INDEX
    Explanations

    references to dates and historical timelines

    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
    laus
    -0.07
    ä¹ĭä¸Ģ
    -0.06
    oft
    -0.06
    achuset
    -0.06
     "..
    -0.06
    äºľ
    -0.06
    wat
    -0.06
    ÏĦά
    -0.06
     microseconds
    -0.06
    ÑĥÑĢÑģ
    -0.06
    POSITIVE LOGITS
    201
    0.11
    202
    0.09
    200
    0.08
    etc
    0.07
     etc
    0.07
     later
    0.07
     others
    0.06
     year
    0.06
    .github
    0.06
    others
    0.06
    Activations Density 0.014%

    No Known Activations