© 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 EvalsExportsAPI 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. 77193
    Prev
    Next
    INDEX
    Explanations

    questions and requirements related to documents and qualifications

    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
    ettle
    -0.07
     lẽ
    -0.07
    UTO
    -0.07
     defiance
    -0.06
    _DEAD
    -0.06
    usz
    -0.06
     isize
    -0.06
    tek
    -0.06
    Insensitive
    -0.06
    vido
    -0.06
    POSITIVE LOGITS
     necessarily
    0.08
     separate
    0.08
     anymore
    0.07
     nor
    0.07
     Formal
    0.07
    achs
    0.07
     explicit
    0.07
     special
    0.07
     Separate
    0.07
     formal
    0.07
    Activations Density 0.025%

    No Known Activations