© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96249
    Prev
    Next
    INDEX
    Explanations

    structural elements and syntax indicators in coding

    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
    .usermodel
    -0.08
    ationToken
    -0.07
    اÙģت
    -0.07
    visor
    -0.07
    UserRole
    -0.07
    VES
    -0.06
    webtoken
    -0.06
    é±
    -0.06
    pill
    -0.06
    arts
    -0.06
    POSITIVE LOGITS
    zk
    0.06
    yun
    0.06
    IMP
    0.06
     Bun
    0.06
     Hearth
    0.06
    ossal
    0.06
    ãĥ³ãĤ¯
    0.06
     narr
    0.06
    ï¼Ĭ
    0.06
     Wag
    0.06
    Activations Density 0.000%

    No Known Activations