© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77410
    Prev
    Next
    INDEX
    Explanations

    instances of the definite article "the" and its significance in context

    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
    bject
    -0.07
    uç
    -0.07
    BorderColor
    -0.06
    ritch
    -0.06
    ÑĤаж
    -0.06
     Sentry
    -0.06
    izr
    -0.06
    Ïģκ
    -0.06
    ervo
    -0.06
    Lint
    -0.06
    POSITIVE LOGITS
    -bottom
    0.07
     bottom
    0.07
    bottom
    0.07
    eken
    0.06
    tracker
    0.06
    \Helpers
    0.06
     çī
    0.06
    DIG
    0.06
    mis
    0.06
    odzi
    0.05
    Activations Density 0.001%

    No Known Activations