© 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. 4848
    Prev
    Next
    INDEX
    Explanations

    block structures and closing brackets in 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
    ãģĵ
    -0.06
    ossip
    -0.06
    LETED
    -0.06
     vie
    -0.06
    omon
    -0.06
    l
    -0.06
    æ¨
    -0.06
    |--
    -0.06
    омÑĸ
    -0.05
    ilater
    -0.05
    POSITIVE LOGITS
    ampo
    0.07
    adian
    0.07
    uzey
    0.07
    Ļ¨
    0.07
    arel
    0.07
    ände
    0.07
    oins
    0.07
    Æ°ng
    0.07
    uxt
    0.07
    246
    0.07
    Activations Density 0.016%

    No Known Activations