© 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. 129867
    Prev
    Next
    INDEX
    Explanations

    formatting and metadata elements typically found in structured documents

    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
    iggs
    -0.08
    oklyn
    -0.07
    aden
    -0.06
     Holt
    -0.06
     IOC
    -0.06
     cock
    -0.06
    owe
    -0.05
     humming
    -0.05
    cock
    -0.05
     Bau
    -0.05
    POSITIVE LOGITS
    aji
    0.07
    isl
    0.07
    #
    0.07
    ึ
    0.07
    étique
    0.07
    ève
    0.06
    -automatic
    0.06
    aises
    0.06
    gue
    0.06
    umnos
    0.06
    Activations Density 0.002%

    No Known Activations