© 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. 72855
    Prev
    Next
    INDEX
    Explanations

    references to programming or technical implementation details

    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
    ruba
    -0.07
    浦
    -0.07
    zar
    -0.07
     expiresIn
    -0.07
    ovah
    -0.07
    üstü
    -0.06
    /bind
    -0.06
     Griffith
    -0.06
    ÑĨвеÑĤ
    -0.06
    637
    -0.06
    POSITIVE LOGITS
     source
    0.11
     code
    0.09
    代çłģ
    0.09
    source
    0.08
    æºIJ
    0.08
     SOURCE
    0.07
     Source
    0.07
     ì½Ķëĵľ
    0.07
     src
    0.07
     publicly
    0.07
    Activations Density 0.033%

    No Known Activations