© 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. 15-LLAMASCOPE-RES-131K
    6. 90268
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics in 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
    eyse
    -0.07
    reib
    -0.07
    uÃŃ
    -0.07
    reater
    -0.07
    aryl
    -0.07
    .vars
    -0.06
    onavir
    -0.06
     Contents
    -0.06
    _Global
    -0.06
    еÑģÑĤи
    -0.06
    POSITIVE LOGITS
    175
    0.07
    435
    0.07
    107
    0.07
     Antoine
    0.07
    lena
    0.07
     total
    0.07
    437
    0.07
    .identity
    0.07
    108
    0.06
    -indent
    0.06
    Activations Density 0.013%

    No Known Activations