© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94814
    Prev
    Next
    INDEX
    Explanations

    tags or phrases used to connect thoughts or ideas together

    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
    riad
    -0.08
    sut
    -0.07
     mush
    -0.07
    ós
    -0.07
    acias
    -0.07
    ÄIJT
    -0.07
    ovsky
    -0.07
    .PackageManager
    -0.07
    airo
    -0.07
    eous
    -0.07
    POSITIVE LOGITS
    cis
    0.07
    彦
    0.07
    undry
    0.06
    651
    0.06
    XL
    0.06
    ISCO
    0.06
    isco
    0.05
    leans
    0.05
    /of
    0.05
    è²Ŀ
    0.05
    Activations Density 0.042%

    No Known Activations