© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28885
    Prev
    Next
    INDEX
    Explanations

    references to theorems and definitions within mathematical texts

    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
    amera
    -0.07
    >NN
    -0.07
    DebugEnabled
    -0.06
    .idea
    -0.06
    GINE
    -0.06
    vine
    -0.06
    {lng
    -0.06
    okol
    -0.06
    CGColor
    -0.06
     extras
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.08
    çºĮ
    0.07
    irsch
    0.07
    enser
    0.06
    lesc
    0.06
    ouis
    0.06
    essler
    0.06
     dec
    0.06
    A
    0.06
     forb
    0.06
    Activations Density 0.082%

    No Known Activations