© 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. 31029
    Prev
    Next
    INDEX
    Explanations

    specific details related to experiences and recommendations

    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
    ë¶
    -0.07
    antity
    -0.07
    ulta
    -0.07
     немного
    -0.07
    ksam
    -0.06
     ONLY
    -0.06
    .unbind
    -0.06
    :title
    -0.06
    >Main
    -0.06
    еко
    -0.06
    POSITIVE LOGITS
     quality
    0.10
     excellent
    0.08
     dynam
    0.07
    -quality
    0.07
    quality
    0.07
     qualidade
    0.07
     great
    0.07
     fen
    0.07
     Quality
    0.07
     superb
    0.07
    Activations Density 0.021%

    No Known Activations