© 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. 15-LLAMASCOPE-RES-131K
    11. 90758
    Prev
    Next
    INDEX
    Explanations

    mentions of non-standard classifications or categories

    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
    eer
    -0.07
    ÂĿ
    -0.07
    ei
    -0.07
    otland
    -0.06
    ej
    -0.06
    tings
    -0.06
    inz
    -0.06
    جع
    -0.06
    ftar
    -0.06
     Hawkins
    -0.06
    POSITIVE LOGITS
    nen
    0.09
    kovi
    0.09
     à¹Ĩ
    0.09
    -existent
    0.08
    enen
    0.08
    chal
    0.08
    nette
    0.08
    ymous
    0.08
    ogram
    0.08
    astery
    0.08
    Activations Density 0.031%

    No Known Activations