© 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. 54788
    Prev
    Next
    INDEX
    Explanations

    references to historical records or documentation

    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
    ela
    -0.07
    ä¼ij
    -0.07
    isel
    -0.06
    çĶ
    -0.06
    amide
    -0.06
     Modular
    -0.06
     Binder
    -0.06
    lettes
    -0.06
     ç§ĭ
    -0.06
    ìĪ
    -0.06
    POSITIVE LOGITS
     census
    0.10
     Directory
    0.10
     Census
    0.10
     listings
    0.09
     listing
    0.09
    @register
    0.09
     registers
    0.09
     directory
    0.08
     directories
    0.08
    directory
    0.08
    Activations Density 0.017%

    No Known Activations