© 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. 5-LLAMASCOPE-RES-131K
    11. 125777
    Prev
    Next
    INDEX
    Explanations

    code structures and definitions related to file handling and project management 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
    onth
    -0.06
    ÏĢλ
    -0.06
    ibble
    -0.06
    tsky
    -0.06
    odge
    -0.06
    iji
    -0.06
     vide
    -0.06
    าà¸
    -0.06
     link
    -0.06
    iasi
    -0.06
    POSITIVE LOGITS
    elay
    0.07
    ordo
    0.07
    cratch
    0.07
    StartPosition
    0.07
    ryn
    0.06
    xdb
    0.06
    éal
    0.06
    raÄį
    0.06
    Lint
    0.06
     fseek
    0.06
    Activations Density 0.045%

    No Known Activations