© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 128867
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, particularly focusing on import statements

    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
    uter
    -0.07
    tres
    -0.07
     Rounds
    -0.06
    ously
    -0.06
    rique
    -0.06
    ä¸Ģç§į
    -0.06
    plete
    -0.06
    ç±
    -0.06
    xfff
    -0.06
    uters
    -0.06
    POSITIVE LOGITS
     minh
    0.06
    _LS
    0.06
    KT
    0.06
     Welfare
    0.06
    CLU
    0.06
    untu
    0.06
    eo
    0.06
    ãĥ³ãĥĸ
    0.06
    leftright
    0.06
    ansas
    0.06
    Activations Density 0.005%

    No Known Activations