© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87929
    Prev
    Next
    INDEX
    Explanations

    references to historical accuracy and its use in modern 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
    ibi
    -0.07
     FLAC
    -0.07
     пеÑĢеп
    -0.06
    steen
    -0.06
     threesome
    -0.06
     âĹij
    -0.06
    oku
    -0.06
    _tail
    -0.06
    çľī
    -0.06
     Sag
    -0.06
    POSITIVE LOGITS
     dancers
    0.08
    ancers
    0.07
     Dance
    0.07
    ekil
    0.07
     dancing
    0.07
     dance
    0.07
     dances
    0.07
     danced
    0.07
    dance
    0.07
     costumes
    0.06
    Activations Density 0.003%

    No Known Activations