© 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. 15-LLAMASCOPE-RES-131K
    11. 103223
    Prev
    Next
    INDEX
    Explanations

    programming language components and their attributes

    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
    HLT
    -0.07
    GLOSS
    -0.07
    umbn
    -0.07
    erno
    -0.07
    coni
    -0.07
    Když
    -0.07
    bab
    -0.07
    ycz
    -0.07
    amiento
    -0.07
    ismet
    -0.07
    POSITIVE LOGITS
    551
    0.06
    .ng
    0.06
     cot
    0.06
    ;↵
    0.05
     conc
    0.05
    Sh
    0.05
    ÑĤаж
    0.05
     luc
    0.05
     fortune
    0.05
    updates
    0.05
    Activations Density 0.012%

    No Known Activations