© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57274
    Prev
    Next
    INDEX
    Explanations

    references to specific products or items, particularly those relating to media or equipment

    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
    åĿĬ
    -0.07
    åĪ°åºķ
    -0.07
     Weiner
    -0.07
    orie
    -0.07
    isl
    -0.07
    CHIP
    -0.06
    ekl
    -0.06
     jä
    -0.06
    acher
    -0.06
    ifter
    -0.06
    POSITIVE LOGITS
     my
    0.09
     purchased
    0.07
    urchase
    0.07
     purchase
    0.07
    æĺ¯æĪij
    0.07
    æĪijçļĦ
    0.06
     Purch
    0.06
     mijn
    0.06
    ιÏİν
    0.06
     Purchase
    0.06
    Activations Density 0.029%

    No Known Activations