© 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. 78505
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in varying contexts, indicating a focus on definite articles

    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
    uml
    -0.06
    sole
    -0.06
    æѦåĻ¨
    -0.06
    _SPE
    -0.06
    çĵľ
    -0.06
    idla
    -0.06
    asco
    -0.06
    anela
    -0.06
    ught
    -0.06
    _CFG
    -0.06
    POSITIVE LOGITS
    chap
    0.07
    isay
    0.06
    oretical
    0.06
    oret
    0.06
    compan
    0.06
    acas
    0.06
    roys
    0.06
     migrationBuilder
    0.06
    ê»
    0.06
    deniz
    0.06
    Activations Density 0.002%

    No Known Activations