© 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. 31044
    Prev
    Next
    INDEX
    Explanations

    references to time and duration

    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
    -0.07
    anth
    -0.06
     Bark
    -0.06
     stage
    -0.06
     conf
    -0.06
     activity
    -0.05
     mess
    -0.05
     d
    -0.05
    675
    -0.05
    /sdk
    -0.05
    POSITIVE LOGITS
    ycz
    0.08
    sie
    0.08
    ëıĮ
    0.08
    agher
    0.08
    bao
    0.07
    ReturnValue
    0.07
    ÑĮогоднÑĸ
    0.07
    ellig
    0.07
    ÑĥÑĤи
    0.07
     baÅŁv
    0.07
    Activations Density 0.002%

    No Known Activations