© 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 EvalsExportsAPI 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. 59007
    Prev
    Next
    INDEX
    Explanations

    numerical values or time indicators

    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
     collo
    -0.06
    isque
    -0.06
    C
    -0.06
    Col
    -0.06
    \
    -0.05
    inky
    -0.05
    high
    -0.05
    col
    -0.05
    ard
    -0.05
     conf
    -0.05
    POSITIVE LOGITS
    luet
    0.09
    SGlobal
    0.08
     yyn
    0.08
    dech
    0.08
    semicolon
    0.08
    RYPT
    0.08
    GuidId
    0.07
    .onViewCreated
    0.07
    -LAST
    0.07
    OfFile
    0.07
    Activations Density 0.002%

    No Known Activations