© 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. 89410
    Prev
    Next
    INDEX
    Explanations

    terms related to website navigation structures

    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
    aget
    -0.07
     Weiner
    -0.06
    onen
    -0.06
    587
    -0.06
    agen
    -0.06
     reuse
    -0.06
    386
    -0.06
    ingham
    -0.06
    odes
    -0.06
     King
    -0.06
    POSITIVE LOGITS
    belt
    0.08
    -expand
    0.08
    alth
    0.07
    ÑĥÑĢÑĭ
    0.07
    urette
    0.07
    toi
    0.07
    eld
    0.06
    tery
    0.06
    agus
    0.06
     ding
    0.06
    Activations Density 0.001%

    No Known Activations