Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11472
    Prev
    Next
    INDEX
    Explanations

    instances of the definite article "the."

    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
    enek
    -0.07
    undry
    -0.07
    ajar
    -0.07
    δει
    -0.06
    ouro
    -0.06
    kek
    -0.06
    edBy
    -0.06
    nutÃŃ
    -0.06
    018
    -0.06
    difference
    -0.06
    POSITIVE LOGITS
     fold
    0.16
     comforts
    0.14
     scene
    0.13
     fray
    0.13
     Fold
    0.13
     confines
    0.13
     comfort
    0.12
     premises
    0.12
     nest
    0.11
     safety
    0.11
    Activations Density 0.053%

    No Known Activations