© 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. 27725
    Prev
    Next
    INDEX
    Explanations

    names and significant historical figures or organizations

    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
    ãģ¾ãģ¾
    -0.06
    anko
    -0.06
    aat
    -0.06
     shortest
    -0.06
    ulan
    -0.06
    ziel
    -0.05
    é¡Į
    -0.05
    id
    -0.05
    lland
    -0.05
    aan
    -0.05
    POSITIVE LOGITS
     later
    0.09
     came
    0.09
     then
    0.08
    SSERT
    0.08
    Later
    0.08
    æĿ¥äºĨ
    0.08
    VERTISE
    0.08
     soon
    0.08
    came
    0.08
     became
    0.07
    Activations Density 0.034%

    No Known Activations