© 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. 83928
    Prev
    Next
    INDEX
    Explanations

    instances of the publishing and updating of works or documents

    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
    achuset
    -0.07
     totiž
    -0.07
    .semantic
    -0.07
    ÂŃn
    -0.06
     ведÑĮ
    -0.06
    umont
    -0.06
    unas
    -0.06
     nues
    -0.06
     ../../../
    -0.06
     minWidth
    -0.06
    POSITIVE LOGITS
     later
    0.12
     subsequently
    0.10
     others
    0.10
     subsequent
    0.10
     thereafter
    0.09
    later
    0.09
     afterwards
    0.08
     später
    0.08
     Later
    0.08
    201
    0.08
    Activations Density 0.039%

    No Known Activations