© 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. 15-LLAMASCOPE-RES-131K
    11. 104087
    Prev
    Next
    INDEX
    Explanations

    details related to personal experiences and historical events

    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
    539
    -0.07
    265
    -0.07
    519
    -0.06
    579
    -0.06
     Learned
    -0.06
    ĵ¨
    -0.06
    .setViewport
    -0.06
    opak
    -0.06
    çŃĴ
    -0.06
    ops
    -0.06
    POSITIVE LOGITS
    panion
    0.07
    ³
    0.07
     pij
    0.07
    collector
    0.07
    親
    0.07
     closure
    0.07
    ainer
    0.07
     physical
    0.07
    nty
    0.06
     Physical
    0.06
    Activations Density 0.069%

    No Known Activations