© 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. 27375
    Prev
    Next
    INDEX
    Explanations

    time durations and event lengths

    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
     Month
    -0.06
    acz
    -0.06
    wake
    -0.06
    Ñģен
    -0.06
     dim
    -0.06
    AZY
    -0.06
     throughout
    -0.05
    etat
    -0.05
    596
    -0.05
    bite
    -0.05
    POSITIVE LOGITS
    -long
    0.11
    å·¦åı³
    0.08
    -plus
    0.08
    ì§ľ
    0.08
    lesh
    0.07
    erea
    0.07
    vic
    0.07
    tÄĽ
    0.07
    -д
    0.07
    -strong
    0.07
    Activations Density 0.010%

    No Known Activations