© 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. 117928
    Prev
    Next
    INDEX
    Explanations

    occurrences of quotation marks in program code

    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
    west
    -0.06
    ész
    -0.06
    ocracy
    -0.06
    oretical
    -0.06
    Mapped
    -0.06
     alone
    -0.06
    urdy
    -0.06
    otti
    -0.05
    aras
    -0.05
     fle
    -0.05
    POSITIVE LOGITS
    emain
    0.08
    uhn
    0.08
    iado
    0.07
    úÄįast
    0.07
    osit
    0.07
    ../../../
    0.06
    pdata
    0.06
     flush
    0.06
    oppable
    0.06
    ırak
    0.06
    Activations Density 0.003%

    No Known Activations