© 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. 4561
    Prev
    Next
    INDEX
    Explanations

    mentions and statistics related to population

    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
    rimp
    -0.08
    jÃŃm
    -0.07
    å°ģ
    -0.07
    æĪIJç«ĭ
    -0.07
    ī´
    -0.07
    æĿŁ
    -0.07
    ollapsed
    -0.07
     tane
    -0.07
    idine
    -0.07
    buie
    -0.07
    POSITIVE LOGITS
     dual
    0.06
    445
    0.06
     growth
    0.06
     Bureau
    0.06
    æł¹
    0.06
     size
    0.06
    amik
    0.05
    shit
    0.05
     race
    0.05
     Eden
    0.05
    Activations Density 0.019%

    No Known Activations