© 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. 107720
    Prev
    Next
    INDEX
    Explanations

    numerical data related to demographics and economic statistics

    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
    /stdc
    -0.09
    unge
    -0.08
    utherford
    -0.07
    emsp
    -0.06
    urat
    -0.06
    adders
    -0.06
    sher
    -0.06
     Oyun
    -0.06
    amburger
    -0.06
    ümÃ¼ÅŁ
    -0.06
    POSITIVE LOGITS
    į
    0.06
    tent
    0.06
     Carson
    0.06
    åĨµ
    0.06
    theid
    0.06
    sob
    0.06
    sen
    0.06
    rador
    0.06
    _flg
    0.06
     ÃĶ
    0.06
    Activations Density 0.001%

    No Known Activations