© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 118160
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and structure

    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
    vak
    -0.07
     obst
    -0.07
     hacks
    -0.07
    pmat
    -0.06
    Å¡ov
    -0.06
    utterstock
    -0.06
    viron
    -0.06
     onBind
    -0.06
    oje
    -0.06
     gener
    -0.06
    POSITIVE LOGITS
    aos
    0.07
    iez
    0.06
    angling
    0.06
    =Value
    0.06
     ------------------------------------------------------------
    0.06
     ------------------------------------------------
    0.06
    kovi
    0.06
     --------------------------------
    0.06
     McB
    0.06
    Ķ
    0.06
    Activations Density 0.008%

    No Known Activations