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

    Neuronpedia

    Jacobian LensNEW
    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. 128865
    Prev
    Next
    INDEX
    Explanations

    references to past events or characters in a story

    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
    å°¿
    -0.07
    eki
    -0.07
    uteur
    -0.07
    ova
    -0.07
    imar
    -0.07
    anel
    -0.07
    ayo
    -0.07
    --[[
    -0.07
     corp
    -0.06
    =".$_
    -0.06
    POSITIVE LOGITS
     _:
    0.06
     blitz
    0.06
     h
    0.05
    contro
    0.05
    extension
    0.05
     Gaw
    0.05
     Newman
    0.05
     Ber
    0.05
    amura
    0.05
    [in
    0.05
    Activations Density 0.005%

    No Known Activations