© 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. 16438
    Prev
    Next
    INDEX
    Explanations

    elements of argumentation centered around logic and claims of evidence

    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
     told
    -0.07
    اعت
    -0.07
     Hubbard
    -0.07
     phon
    -0.06
    ï¼Ĭ
    -0.05
     eventual
    -0.05
    event
    -0.05
     Orbit
    -0.05
    phon
    -0.05
    tractor
    -0.05
    POSITIVE LOGITS
    Argument
    0.08
    pollo
    0.08
     Argument
    0.08
     arguments
    0.07
    ../../../../
    0.07
    arguments
    0.07
     Arguments
    0.07
    ystate
    0.07
     argument
    0.07
    argument
    0.07
    Activations Density 0.003%

    No Known Activations