© 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. 30260
    Prev
    Next
    INDEX
    Explanations

    references to organizational entities and divisions within a hierarchy

    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
     Dün
    -0.09
     sona
    -0.08
    enson
    -0.08
    jour
    -0.07
    roj
    -0.07
    олÑİ
    -0.07
    ë¹Ī
    -0.07
    aceous
    -0.07
     Declarations
    -0.07
    oteca
    -0.07
    POSITIVE LOGITS
    al
    0.07
    /div
    0.07
    /Branch
    0.06
    leur
    0.06
    ted
    0.06
    ized
    0.06
    ç½²
    0.06
    88
    0.06
    branch
    0.06
    aker
    0.06
    Activations Density 0.027%

    No Known Activations