© 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. 81037
    Prev
    Next
    INDEX
    Explanations

    terms related to searching and queries

    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
    amo
    -0.07
    ao
    -0.07
    /from
    -0.06
    alo
    -0.06
    an
    -0.06
    веÑī
    -0.06
    è¡¡
    -0.06
    eco
    -0.06
    che
    -0.06
    æ¬Ĭ
    -0.06
    POSITIVE LOGITS
     for
    0.09
    eses
    0.08
    ForResult
    0.07
    beth
    0.07
    aises
    0.07
    archive
    0.07
    ulty
    0.07
    帯
    0.07
    repos
    0.07
    ajes
    0.06
    Activations Density 0.009%

    No Known Activations