© 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. 60826
    Prev
    Next
    INDEX
    Explanations

    references to items and inventory mechanics in a game

    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
    oader
    -0.08
    ç¹Ķ
    -0.07
    batim
    -0.07
     اختÙĦ
    -0.07
    ohon
    -0.07
    cly
    -0.07
    undler
    -0.07
     Kỳ
    -0.07
    creativecommons
    -0.07
    pread
    -0.07
    POSITIVE LOGITS
     here
    0.06
    here
    0.06
     worthwhile
    0.06
     Sloan
    0.06
    291
    0.06
    astery
    0.05
    BASH
    0.05
     anale
    0.05
     waters
    0.05
     Considering
    0.05
    Activations Density 0.004%

    No Known Activations