© 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 EvalsExportsAPI 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. 85514
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts or elements related to data states and error handling

    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
    ema
    -0.07
    à¤Ĥध
    -0.06
     Rol
    -0.06
    parator
    -0.06
    iloc
    -0.06
    icho
    -0.06
    affer
    -0.06
     Sig
    -0.05
    linkplain
    -0.05
    yonel
    -0.05
    POSITIVE LOGITS
    仲
    0.07
    į
    0.07
    аÑĢам
    0.07
    \OptionsResolver
    0.07
    nish
    0.06
    太éĥİ
    0.06
    iams
    0.06
    ìĬ¨
    0.06
    istrator
    0.06
    atas
    0.06
    Activations Density 0.014%

    No Known Activations