© 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. 15130
    Prev
    Next
    INDEX
    Explanations

    instances of the word "The" in various contexts

    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
    actly
    -0.07
    lah
    -0.07
    лÑİ
    -0.07
    usan
    -0.07
    lum
    -0.06
    æĸ
    -0.06
    uter
    -0.06
     behalf
    -0.06
     OTHERWISE
    -0.06
    standing
    -0.06
    POSITIVE LOGITS
    oretical
    0.13
    ories
    0.11
    odore
    0.11
    atre
    0.10
    orie
    0.09
    orem
    0.09
    oret
    0.09
    odor
    0.08
     célib
    0.07
     adulte
    0.07
    Activations Density 0.033%

    No Known Activations