© 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. 41337
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to finance and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Domain-specific terminology, technical jargon, proper names, or specialized vocabulary that has particular significance within their respective contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    icie
    -0.06
    аÑĩе
    -0.06
    ãĥ¬ãĥ¼
    -0.06
     noqa
    -0.06
    ofire
    -0.06
    tesy
    -0.06
    ymbols
    -0.06
    indsight
    -0.06
    illion
    -0.06
    orde
    -0.05
    POSITIVE LOGITS
    STITUTE
    0.09
    loff
    0.07
    \admin
    0.07
    IVES
    0.07
    GLfloat
    0.07
    ÙħاÙĨÛĮ
    0.07
    cctor
    0.07
     завд
    0.06
    @student
    0.06
    PathParam
    0.06
    Activations Density 0.484%

    No Known Activations