© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    phrases related to structured information and research methodologies

    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
    uais
    -0.07
    cken
    -0.07
     hence
    -0.07
    phis
    -0.07
    avian
    -0.06
    jee
    -0.06
    ensch
    -0.06
     à¤ĩसल
    -0.06
    aus
    -0.06
    äng
    -0.06
    POSITIVE LOGITS
    è¿Ļ个
    0.09
    éĢĻ
    0.08
     <<<
    0.08
    ï¼Į该
    0.08
     which
    0.07
    which
    0.07
     These
    0.07
    该
    0.07
    abr
    0.07
    è¿ĻäºĽ
    0.07
    Activations Density 0.096%

    No Known Activations