Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83022
    Prev
    Next
    INDEX
    Explanations

    names of notable athletes and musicians

    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
    èo
    -0.09
    説
    -0.08
    INCLUDED
    -0.07
    воÑİ
    -0.07
    ÐłÐĿ
    -0.07
    ëĿ
    -0.07
    undef
    -0.07
    (æ°´
    -0.07
    é»
    -0.07
    ï¼īãģ¯
    -0.07
    POSITIVE LOGITS
    erer
    0.06
     Parts
    0.06
     (
    0.06
    and
    0.06
    cha
    0.06
    pard
    0.06
    loo
    0.06
    i
    0.06
     and
    0.06
     ?
    0.06
    Activations Density 0.021%

    No Known Activations