© 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. 72274
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related language

    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
    outil
    -0.07
    obus
    -0.07
    aign
    -0.07
    hait
    -0.07
    .scala
    -0.07
    anine
    -0.07
    iful
    -0.07
    _unix
    -0.06
    ceae
    -0.06
    /Instruction
    -0.06
    POSITIVE LOGITS
     Baltimore
    0.08
     Gul
    0.07
     Maryland
    0.07
    .dll
    0.06
    (hwnd
    0.06
     Win
    0.06
    ARB
    0.06
     Freeman
    0.06
    _dll
    0.06
     Washington
    0.06
    Activations Density 0.034%

    No Known Activations