© 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. 79350
    Prev
    Next
    INDEX
    Explanations

    references to specific years and historical 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
     tonight
    -0.08
    ewing
    -0.07
     tomorrow
    -0.06
    alach
    -0.06
    aguay
    -0.06
     hack
    -0.06
    eway
    -0.06
     save
    -0.06
     overhead
    -0.06
    ertz
    -0.06
    POSITIVE LOGITS
     era
    0.10
     dönemde
    0.09
    Peak
    0.08
     Era
    0.08
    post
    0.07
     shortly
    0.07
     periodo
    0.07
     dobÄĽ
    0.07
     peak
    0.07
    à¹īà¸ĩ
    0.07
    Activations Density 0.033%

    No Known Activations