© 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. 126221
    Prev
    Next
    INDEX
    Explanations

    references to universities and colleges

    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
    çĿĽ
    -0.06
    âĢ¦↵
    -0.06
    ,âĢ¦
    -0.06
    Sparse
    -0.06
    âĢ¦↵↵
    -0.06
     [âĢ¦]↵
    -0.06
    OLS
    -0.06
    645
    -0.06
    erring
    -0.06
    =wx
    -0.05
    POSITIVE LOGITS
    воÑİ
    0.07
    aset
    0.07
     fitte
    0.06
    arsers
    0.06
    istogram
    0.06
    atrix
    0.06
     ëĸł
    0.06
    isposable
    0.06
    è¼Ŀ
    0.06
    amber
    0.06
    Activations Density 0.074%

    No Known Activations