© 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. 94879
    Prev
    Next
    INDEX
    Explanations

    phrases associated with the acquisition and funding of resources or equipment

    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
    antan
    -0.08
     JsonSerializer
    -0.07
    endor
    -0.06
    vere
    -0.06
    enko
    -0.06
    uestra
    -0.06
    AbsolutePath
    -0.06
    iness
    -0.06
    antha
    -0.06
    oting
    -0.06
    POSITIVE LOGITS
     Kraj
    0.07
    egin
    0.07
     *&
    0.07
    _contin
    0.06
    iets
    0.06
    luet
    0.06
    leans
    0.06
    ovna
    0.06
     butterfly
    0.06
    æį
    0.06
    Activations Density 0.025%

    No Known Activations