© 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. 15-LLAMASCOPE-RES-131K
    11. 86910
    Prev
    Next
    INDEX
    Explanations

    code-related content involving class or method declarations

    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
    TypeID
    -0.07
    agged
    -0.06
     Roe
    -0.06
    TED
    -0.06
    oyer
    -0.06
     Gutenberg
    -0.06
    TypeInfo
    -0.06
    еÑģÑı
    -0.06
    istringstream
    -0.06
    nw
    -0.06
    POSITIVE LOGITS
     return
    0.07
    isci
    0.07
    intColor
    0.06
    à¹Ĥà¸Ħ
    0.06
    ftime
    0.06
    ardown
    0.06
    astle
    0.06
     Conj
    0.06
    -Core
    0.06
    undler
    0.05
    Activations Density 0.005%

    No Known Activations