© 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. 87568
    Prev
    Next
    INDEX
    Explanations

    references to the "Lancet" journal and related articles

    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
    enever
    -0.07
    holding
    -0.06
    sol
    -0.06
    itsu
    -0.06
    ulas
    -0.06
    $MESS
    -0.06
    hold
    -0.06
     Borg
    -0.06
    enticator
    -0.06
     sophistic
    -0.06
    POSITIVE LOGITS
    mÃŃt
    0.07
    ijkl
    0.07
    ijn
    0.07
    ús
    0.07
    Setter
    0.07
    ãĤ¸ãĤª
    0.07
    brief
    0.06
    èªĮ
    0.06
    MOVED
    0.06
    BuilderFactory
    0.06
    Activations Density 0.003%

    No Known Activations