© 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 EvalsExportsinterp-engineNEWAPI 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. 81948
    Prev
    Next
    INDEX
    Explanations

    specific high-frequency words and phrases, particularly related to requirements and user interactions

    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
    ioni
    -0.07
     Kostenlose
    -0.07
    onium
    -0.05
    ãĥ¼ãĥķ
    -0.05
     Licensed
    -0.05
    견
    -0.05
    acb
    -0.05
    DELAY
    -0.05
    onte
    -0.05
    ugu
    -0.05
    POSITIVE LOGITS
     only
    0.28
     ONLY
    0.28
     exclusively
    0.25
    only
    0.25
    -only
    0.24
    ONLY
    0.23
     solely
    0.23
    _only
    0.23
    Only
    0.23
     Only
    0.23
    Activations Density 0.001%

    No Known Activations