© 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. 92322
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to geographical information

    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
    202
    -0.10
     GDPR
    -0.06
    .
    -0.06
     https
    -0.06
    ube
    -0.06
    ï¸ı
    -0.06
    https
    -0.06
    atch
    -0.06
    Û²Û°Û²
    -0.06
    finity
    -0.06
    POSITIVE LOGITS
    smarty
    0.08
    cntl
    0.07
    //{{
    0.07
    ÄĽr
    0.07
    اÙĨÙĩ
    0.07
    pcf
    0.07
    mpl
    0.07
     ÑĦакÑĤ
    0.07
    KANJI
    0.07
    Ware
    0.07
    Activations Density 0.044%

    No Known Activations