© 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 EvalsExportsinterp-engineNEWAPI 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. 92188
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps associated with events

    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
     hyp
    -0.06
    âĢ¦↵
    -0.06
     –
    -0.06
     As
    -0.06
     “
    -0.06
     do
    -0.06
    arb
    -0.06
     --
    -0.06
    avan
    -0.06
     "
    -0.06
    POSITIVE LOGITS
    isten
    0.09
    (SP
    0.08
    ubar
    0.08
    éłĵ
    0.07
    Ñİк
    0.07
    оло
    0.07
    Å¡ov
    0.07
    Assignable
    0.07
    èĻ
    0.07
    ISK
    0.07
    Activations Density 0.014%

    No Known Activations