© 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. 14510
    Prev
    Next
    INDEX
    Explanations

    common function words and symbols used in code or structure definitions

    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
     entitled
    -0.06
     Ning
    -0.06
    othy
    -0.05
     titled
    -0.05
    _PUR
    -0.05
     Dam
    -0.05
     called
    -0.05
     reviews
    -0.05
     list
    -0.05
    ever
    -0.05
    POSITIVE LOGITS
     our
    0.12
     nuestro
    0.10
     ours
    0.10
    æĪij们çļĦ
    0.10
     наÑĪей
    0.10
     noss
    0.09
     nuestra
    0.09
     nossa
    0.09
     nosso
    0.09
     nostra
    0.09
    Activations Density 0.001%

    No Known Activations