© 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. 72579
    Prev
    Next
    INDEX
    Explanations

    directives related to content management and editing instructions

    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
    bial
    -0.06
    abor
    -0.06
    igh
    -0.06
    abar
    -0.06
    aven
    -0.06
    anch
    -0.06
    ika
    -0.06
    ola
    -0.06
    дÑĥ
    -0.06
     bat
    -0.06
    POSITIVE LOGITS
    imas
    0.07
    ifar
    0.07
     Vác
    0.07
     ÙģÙĪ
    0.07
    è®
    0.07
    ître
    0.07
    zcze
    0.07
     CharSequence
    0.07
     onDataChange
    0.06
     EÅŁ
    0.06
    Activations Density 0.001%

    No Known Activations