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. 43703
    Prev
    Next
    INDEX
    Explanations

    various forms of words, particularly nouns and proper nouns in the context of names

    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
     An
    -0.10
     a
    -0.10
     In
    -0.10
     N
    -0.09
     S
    -0.09
     m
    -0.09
     A
    -0.09
     G
    -0.09
     Ver
    -0.09
     T
    -0.08
    POSITIVE LOGITS
     ÐĴона
    0.12
     ван
    0.12
     ÐĶжон
    0.11
     Ðļоли
    0.11
     ÑĦон
    0.11
     Шев
    0.11
     Чи
    0.10
     Як
    0.10
     ÐļÑĢи
    0.10
     Том
    0.10
    Activations Density 0.013%

    No Known Activations