© 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. 2391
    Prev
    Next
    INDEX
    Explanations

    references to trademark-related terms

    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
    lfw
    -0.07
    кол
    -0.06
    вол
    -0.06
    hd
    -0.06
    agues
    -0.06
    ensem
    -0.06
     path
    -0.06
    ¤í
    -0.06
    onnement
    -0.06
    antz
    -0.06
    POSITIVE LOGITS
     AudioClip
    0.07
     Roller
    0.07
    ajo
    0.07
    ustr
    0.07
     services
    0.07
    ring
    0.07
    ropa
    0.06
    è°·
    0.06
    ixo
    0.06
    mods
    0.06
    Activations Density 0.000%

    No Known Activations