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. 43586
    Prev
    Next
    INDEX
    Explanations

    terms associated with caffeine consumption and its effects

    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
     retard
    -0.06
    ‘
    -0.06
     retarded
    -0.06
    Âħ
    -0.06
    åħįè´¹
    -0.06
     hoá
    -0.06
     ‘
    -0.06
    annes
    -0.06
    ³³
    -0.06
    avourites
    -0.06
    POSITIVE LOGITS
     
    0.10
     âĢĮ
    0.09
     ðŁij
    0.09
     Trusted
    0.09
     HuffPost
    0.08
     ðŁ
    0.08
    ï¸ı
    0.08
     ðŁĶ
    0.08
     experts
    0.08
     mayo
    0.08
    Activations Density 0.020%

    No Known Activations