© 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. 129581
    Prev
    Next
    INDEX
    Explanations

    code snippets or syntax elements within programming contexts

    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
     bidi
    -0.06
    ©
    -0.06
    aeper
    -0.06
    iaux
    -0.06
    ↵
    -0.06
    (.)
    -0.06
    fold
    -0.06
    pars
    -0.06
    ække
    -0.06
    ÂĽ
    -0.05
    POSITIVE LOGITS
    /'
    0.09
    ãĢģ“
    0.07
    /{{
    0.07
    Č
    0.07
    ίνη
    0.07
    tempts
    0.07
    lein
    0.07
    ãĥĥãĥĪ
    0.07
    ergic
    0.07
    ions
    0.06
    Activations Density 0.024%

    No Known Activations