© 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. 73481
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names, especially related to sports

    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
    ingu
    -0.06
    ocaly
    -0.06
    ilst
    -0.06
    oin
    -0.06
    Textures
    -0.06
    tero
    -0.06
    unar
    -0.06
    anlı
    -0.06
    :
    -0.06
    eware
    -0.05
    POSITIVE LOGITS
     during
    0.09
    during
    0.08
    icaret
    0.07
    eated
    0.07
    üm
    0.07
    ãģĦãĤĭ
    0.07
     durante
    0.07
     atIndex
    0.07
    CHANT
    0.06
    \Migration
    0.06
    Activations Density 0.013%

    No Known Activations