© 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. 126718
    Prev
    Next
    INDEX
    Explanations

    references to venture capital and related investment activities

    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
    ãĥĨãĥ«
    -0.09
    nie
    -0.08
    amba
    -0.08
    áce
    -0.07
    nya
    -0.07
    /AFP
    -0.07
    olley
    -0.07
    isson
    -0.07
    achines
    -0.07
    омеÑĢ
    -0.07
    POSITIVE LOGITS
    ously
    0.10
    ous
    0.09
     capitalists
    0.08
    prise
    0.07
     capitalist
    0.07
    itial
    0.07
    urs
    0.07
    forth
    0.07
    /start
    0.07
    bilt
    0.06
    Activations Density 0.006%

    No Known Activations