© 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. 117201
    Prev
    Next
    INDEX
    Explanations

    elements related to literature and academic references

    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
    lid
    -0.06
    اج
    -0.06
    /if
    -0.06
    chodu
    -0.06
     SH
    -0.06
    chod
    -0.06
    iqu
    -0.06
     pik
    -0.06
    ãģıãģł
    -0.06
     Alexandre
    -0.06
    POSITIVE LOGITS
    inue
    0.07
    ServiceImpl
    0.07
    ä¹İ
    0.07
    upos
    0.06
    bery
    0.06
    ös
    0.06
    /features
    0.06
    缮ãģ®
    0.06
    asca
    0.06
    hib
    0.06
    Activations Density 0.030%

    No Known Activations