© 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. 16970
    Prev
    Next
    INDEX
    Explanations

    coding terms related to structure and organization in programming

    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
     zel
    -0.07
    .Butter
    -0.07
    ãĥ
    -0.06
    /false
    -0.06
    liest
    -0.06
    ÐļТ
    -0.06
    _RPC
    -0.06
    æīķ
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
    lify
    -0.06
    POSITIVE LOGITS
    åĮ
    0.07
    ationale
    0.06
    ijn
    0.06
    807
    0.06
    enery
    0.06
    anel
    0.06
    uri
    0.06
     Negot
    0.06
     conjug
    0.06
    istrict
    0.06
    Activations Density 0.008%

    No Known Activations