© 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. 94884
    Prev
    Next
    INDEX
    Explanations

    connections to specific actions or conditions that have implications for other contexts

    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
    illaume
    -0.06
    ez
    -0.06
     accordingly
    -0.06
    ÑĢаб
    -0.06
    instead
    -0.06
    steen
    -0.06
    ?key
    -0.06
    QUI
    -0.05
    ipi
    -0.05
     *}
    -0.05
    POSITIVE LOGITS
    adow
    0.08
    inese
    0.07
    atak
    0.07
    wiki
    0.07
    ird
    0.07
    bits
    0.07
    ould
    0.06
    akis
    0.06
    ijn
    0.06
     ÙĨÙģس
    0.06
    Activations Density 0.008%

    No Known Activations