© 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. 39368
    Prev
    Next
    INDEX
    Explanations

    negative values and specific formatting related to measurements or dimensions

    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
     tertiary
    -0.06
    arkin
    -0.06
    ahl
    -0.06
    enberg
    -0.06
    enko
    -0.06
    ailer
    -0.06
    /tests
    -0.06
     [|
    -0.06
    ember
    -0.06
    .ActionBar
    -0.06
    POSITIVE LOGITS
     sight
    0.07
    orris
    0.06
    ilated
    0.06
    ebo
    0.06
    à¥Ľ
    0.06
    .emf
    0.06
    ol
    0.06
     dil
    0.06
    اط
    0.06
    jist
    0.06
    Activations Density 0.007%

    No Known Activations