© 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. 117243
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and their attributes

    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
    rzy
    -0.08
    iniz
    -0.08
    essian
    -0.08
    kaar
    -0.08
    nyder
    -0.07
    nze
    -0.07
    ãģ¡ãĤĥ
    -0.07
    plode
    -0.07
    onders
    -0.07
    itulo
    -0.07
    POSITIVE LOGITS
    a
    0.09
     a
    0.08
     fault
    0.07
    alt
    0.07
    <a
    0.06
    	a
    0.06
     link
    0.06
    keh
    0.06
    aling
    0.06
    а
    0.06
    Activations Density 0.004%

    No Known Activations