© 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. 15310
    Prev
    Next
    INDEX
    Explanations

    HTML or markup language tags

    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
    ince
    -0.06
    flash
    -0.06
    ands
    -0.06
    ll
    -0.06
     duplicate
    -0.06
    çīĪ
    -0.06
    StateChanged
    -0.06
     msgid
    -0.06
    ores
    -0.06
    NAL
    -0.06
    POSITIVE LOGITS
    ugo
    0.08
    å¹ħ
    0.06
     Unidos
    0.06
     EAR
    0.06
    álu
    0.06
    eyer
    0.06
    WithMany
    0.06
     reck
    0.06
    æŀ
    0.06
    arto
    0.06
    Activations Density 0.018%

    No Known Activations