© 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. 70849
    Prev
    Next
    INDEX
    Explanations

    function definitions and their structures in code

    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
     Chap
    -0.08
     Davidson
    -0.06
    iec
    -0.06
    ç¿Ĵ
    -0.06
    inary
    -0.06
    leans
    -0.06
    hec
    -0.06
     cigar
    -0.06
     Cha
    -0.06
     Steele
    -0.06
    POSITIVE LOGITS
    nesc
    0.09
    .gf
    0.07
    ALSE
    0.07
     æ¹
    0.07
    aaS
    0.06
    -REAL
    0.06
    OX
    0.06
    ionage
    0.06
    ä¼Ŀ
    0.06
    acom
    0.06
    Activations Density 0.011%

    No Known Activations