© 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. 76831
    Prev
    Next
    INDEX
    Explanations

    references to seeing, looking, or observing people, places, or activities

    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
    ka
    -0.06
    afs
    -0.06
    erten
    -0.06
    สำà¹Ģร
    -0.06
    icions
    -0.06
    ux
    -0.06
    slu
    -0.06
    asa
    -0.06
     Formal
    -0.06
    acter
    -0.06
    POSITIVE LOGITS
     how
    0.09
    ograd
    0.07
     Andersen
    0.07
    latest
    0.07
     everything
    0.07
     latest
    0.07
    lage
    0.07
    amation
    0.06
    .telegram
    0.06
    idir
    0.06
    Activations Density 0.016%

    No Known Activations