© 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. 17-LLAMASCOPE-RES-131K
    11. 72080
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals named Marc

    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
    erland
    -0.08
    ongyang
    -0.08
    perature
    -0.07
    rippling
    -0.07
    entials
    -0.07
    rient
    -0.07
    ocking
    -0.07
    eci
    -0.07
    ration
    -0.07
    stants
    -0.07
    POSITIVE LOGITS
    ussen
    0.09
    ie
    0.07
    anton
    0.07
    ion
    0.07
    ia
    0.07
    HQ
    0.07
    angelo
    0.06
    ailed
    0.06
    ا
    0.06
     Duel
    0.06
    Activations Density 0.006%

    No Known Activations