© 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. 76580
    Prev
    Next
    INDEX
    Explanations

    terms associated with technical processes and methodologies

    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
    öm
    -0.07
    osate
    -0.07
     kvin
    -0.07
    ieu
    -0.07
    icer
    -0.07
    olah
    -0.07
    ilet
    -0.07
    untas
    -0.07
    thew
    -0.07
    tainment
    -0.06
    POSITIVE LOGITS
     Bab
    0.07
    CEF
    0.06
    xBB
    0.06
    EDA
    0.06
    ãĥ¼ãĥĸ
    0.06
    ocha
    0.06
     Socorro
    0.06
    gu
    0.06
     Yard
    0.05
    itical
    0.05
    Activations Density 0.000%

    No Known Activations