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. 22-LLAMASCOPE-RES-131K
    6. 5735
    Prev
    Next
    INDEX
    Explanations

    elements of numerical or structural notation in text

    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
    lady
    -0.06
    eurs
    -0.06
    ect
    -0.06
    eil
    -0.06
    frauen
    -0.06
    æ±Ĥ
    -0.06
    phylum
    -0.05
     Jord
    -0.05
    etter
    -0.05
    ä¹Ļ
    -0.05
    POSITIVE LOGITS
     лиÑĪ
    0.08
    urdy
    0.07
     Äįeský
    0.07
    LAG
    0.07
    trfs
    0.07
     ped
    0.07
     pil
    0.07
     polÃŃtica
    0.07
     diss
    0.07
     figura
    0.07
    Activations Density 0.006%

    No Known Activations