© 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. 71158
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications 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
    abbr
    -0.07
    eteria
    -0.07
    énom
    -0.07
    Neo
    -0.07
     Pass
    -0.06
    nodeName
    -0.06
    issen
    -0.06
    QualifiedName
    -0.06
     Musk
    -0.06
    ifestyles
    -0.06
    POSITIVE LOGITS
    .ArgumentParser
    0.08
    æ¦
    0.07
     creep
    0.07
     physics
    0.07
    Physics
    0.07
    /epl
    0.06
     PHYS
    0.06
     binh
    0.06
    mie
    0.06
     Physics
    0.06
    Activations Density 0.151%

    No Known Activations