© 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 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. 17-LLAMASCOPE-RES-131K
    11. 118679
    Prev
    Next
    INDEX
    Explanations

    references to numerical values, particularly focusing on counts and identifiers

    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
    uzu
    -0.07
    ough
    -0.07
    ing
    -0.07
    inx
    -0.07
    è§
    -0.07
    ptal
    -0.06
    ạc
    -0.06
    comes
    -0.06
    gün
    -0.06
    ymi
    -0.06
    POSITIVE LOGITS
    ity
    0.08
    ucci
    0.08
    aken
    0.07
    jourd
    0.07
    alogy
    0.07
    ellan
    0.07
     discrepan
    0.07
    ulp
    0.07
     rig
    0.06
     latter
    0.06
    Activations Density 0.036%

    No Known Activations