© 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. 79305
    Prev
    Next
    INDEX
    Explanations

    references to organizations, groups, and institutional structures

    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
    ève
    -0.07
     etc
    -0.07
    ifest
    -0.07
    بÙĪاسطة
    -0.07
    нÑİ
    -0.07
    пÑĢа
    -0.07
    leigh
    -0.07
    IBC
    -0.07
    ायन
    -0.06
    etc
    -0.06
    POSITIVE LOGITS
    :
    0.15
    nam
    0.15
     viz
    0.13
     namely
    0.12
    viz
    0.11
     ÛĮعÙĨÛĮ
    0.09
    åĪĨåĪ«
    0.08
     nam
    0.08
    *:
    0.08
     (
    0.08
    Activations Density 0.208%

    No Known Activations