© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89029
    Prev
    Next
    INDEX
    Explanations

    references to main or significant characters or elements in a narrative

    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
    kla
    -0.08
    uese
    -0.07
    áp
    -0.07
    Ø´ÙħاÙĦÛĮ
    -0.07
    MOOTH
    -0.07
    ISCO
    -0.07
    okers
    -0.07
    esser
    -0.06
    shal
    -0.06
     Barnett
    -0.06
    POSITIVE LOGITS
    /head
    0.08
    /main
    0.06
    stream
    0.06
    cn
    0.06
    ingo
    0.06
    /Sub
    0.06
     thrust
    0.06
    mist
    0.06
    stay
    0.06
    /root
    0.06
    Activations Density 0.004%

    No Known Activations