© 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. 77431
    Prev
    Next
    INDEX
    Explanations

    numerical values related to counts and sizes in programming contexts

    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
    /rem
    -0.07
    aign
    -0.06
     respondsToSelector
    -0.06
     Fior
    -0.06
    uman
    -0.06
    æµľ
    -0.06
    串
    -0.06
     Miles
    -0.06
    escaping
    -0.06
     ÑĤек
    -0.06
    POSITIVE LOGITS
    íģ¼
    0.07
    fold
    0.06
    次
    0.06
    /high
    0.06
    865
    0.06
    ugen
    0.06
    =size
    0.06
    =len
    0.06
    Mui
    0.06
     mug
    0.06
    Activations Density 0.148%

    No Known Activations