© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 39958
    Prev
    Next
    INDEX
    Explanations

    identifiers and properties related to data structures or programming elements

    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
    itou
    -0.06
     [=
    -0.06
     Rac
    -0.06
    ToProps
    -0.06
     Banner
    -0.06
    á»ĵn
    -0.06
    .Env
    -0.05
    EMAIL
    -0.05
     Kara
    -0.05
    LOPT
    -0.05
    POSITIVE LOGITS
    isContained
    0.07
    uzzy
    0.07
     sup
    0.07
    abox
    0.07
     supers
    0.06
    actory
    0.06
    soever
    0.06
    noDB
    0.06
    brig
    0.06
    ÑĭÑģ
    0.06
    Activations Density 0.010%

    No Known Activations