© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 103403
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and client APIs

    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
    ery
    -0.06
    agner
    -0.06
    sv
    -0.06
     Ag
    -0.05
    icker
    -0.05
     form
    -0.05
     elev
    -0.05
    oken
    -0.05
     the
    -0.05
    atar
    -0.05
    POSITIVE LOGITS
    BOSE
    0.09
    eza
    0.09
    лÑĥг
    0.08
    ableObject
    0.08
    nul
    0.07
    bose
    0.07
    eparator
    0.07
    Interop
    0.07
    ValueType
    0.07
    áct
    0.07
    Activations Density 0.000%

    No Known Activations