© 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. 69455
    Prev
    Next
    INDEX
    Explanations

    syntax structures and closing braces in 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
    antar
    -0.07
    rael
    -0.06
    bourg
    -0.06
     cha
    -0.06
     Belle
    -0.06
    hammer
    -0.06
    street
    -0.06
    аÑĢÑĸ
    -0.06
    oggler
    -0.06
    ych
    -0.06
    POSITIVE LOGITS
     Zot
    0.08
    elines
    0.07
    ãĤ¤ãĥ«
    0.07
    едаг
    0.07
    ignon
    0.07
    strand
    0.07
    inus
    0.07
    882
    0.06
    hetto
    0.06
     rewind
    0.06
    Activations Density 0.014%

    No Known Activations