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. 44085
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verbs "have" and "be" in various forms

    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
     recently
    -0.15
     earlier
    -0.14
     recent
    -0.14
    recent
    -0.13
     lately
    -0.12
     later
    -0.11
     yesterday
    -0.11
     Recently
    -0.11
     today
    -0.10
     currently
    -0.10
    POSITIVE LOGITS
     steadily
    0.12
     increasingly
    0.11
     progressively
    0.11
     gradually
    0.11
     intermitt
    0.11
     continuously
    0.10
     repeatedly
    0.10
     consistently
    0.10
     slowly
    0.10
     continually
    0.10
    Activations Density 0.097%

    No Known Activations