© 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. 9-LLAMASCOPE-RES-131K
    11. 97581
    Prev
    Next
    INDEX
    Explanations

    numerical references or data in scientific contexts

    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
     wre
    -0.07
     Radi
    -0.06
    .fm
    -0.06
     cow
    -0.06
    hide
    -0.06
     radi
    -0.06
    uch
    -0.06
     Im
    -0.05
     hid
    -0.05
    axe
    -0.05
    POSITIVE LOGITS
    íĨłíĨł
    0.09
    èĬ¬
    0.08
    IGHL
    0.07
    iska
    0.07
    iou
    0.07
    ivas
    0.07
    baÅŁ
    0.07
    (éĩij
    0.07
    æŀļ
    0.07
    enario
    0.07
    Activations Density 0.000%

    No Known Activations