© 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. 128259
    Prev
    Next
    INDEX
    Explanations

    specific chemical or technical terms and their applications

    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
    owell
    -0.08
    esch
    -0.07
    edis
    -0.07
    ckill
    -0.07
    elmet
    -0.07
    елÑİ
    -0.07
    wahl
    -0.07
    ughs
    -0.07
    edl
    -0.07
    ellers
    -0.06
    POSITIVE LOGITS
    ãĢħ
    0.08
    anny
    0.08
    timing
    0.07
    anna
    0.07
    liers
    0.06
    ana
    0.06
    ogl
    0.06
    plate
    0.06
    cul
    0.06
     dozen
    0.06
    Activations Density 0.002%

    No Known Activations