© 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. 71506
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to competitions and events

    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
    ocos
    -0.06
    ÙĪارÙĩ
    -0.06
    ëĿ¼ëıĦ
    -0.06
     tot
    -0.06
    ĥ½
    -0.06
    нÑıÑĤ
    -0.05
    orum
    -0.05
    omorphic
    -0.05
    rous
    -0.05
     same
    -0.05
    POSITIVE LOGITS
     history
    0.09
    background
    0.08
    history
    0.08
     background
    0.08
    oleon
    0.08
    specific
    0.07
     backgrounds
    0.07
    iola
    0.07
    ubat
    0.07
     procedure
    0.07
    Activations Density 0.023%

    No Known Activations