© 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. 31207
    Prev
    Next
    INDEX
    Explanations

    syntax elements and keywords related to programming code

    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
    oret
    -0.07
    isay
    -0.07
    brid
    -0.07
    oš
    -0.06
    argas
    -0.06
    rieg
    -0.06
    âl
    -0.06
    dictions
    -0.06
    uzu
    -0.06
    ãĢħ
    -0.06
    POSITIVE LOGITS
     Dod
    0.06
    ftype
    0.06
    _NOP
    0.06
    placer
    0.06
    SHA
    0.06
     Domin
    0.06
     Bris
    0.06
    NotFoundException
    0.06
     Prince
    0.05
    à¹ĥ
    0.05
    Activations Density 0.000%

    No Known Activations