© 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 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. 76615
    Prev
    Next
    INDEX
    Explanations

    numerals and numerical sequences

    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
    ÅĻi
    -0.07
    èm
    -0.06
    .partial
    -0.06
    phinx
    -0.06
    åİ»äºĨ
    -0.06
    cmds
    -0.06
    ingleton
    -0.06
    .Exchange
    -0.06
    _sess
    -0.06
    ())[
    -0.06
    POSITIVE LOGITS
    ippo
    0.07
    ique
    0.07
    ium
    0.06
     Millenn
    0.06
     dna
    0.06
    anno
    0.06
     Clarkson
    0.06
     Mein
    0.06
    igon
    0.06
     Declarations
    0.06
    Activations Density 0.001%

    No Known Activations