© 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 EvalsExportsinterp-engineNEWAPI 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. 4703
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and function calls in programming or scripting contexts

    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
    libft
    -0.08
    eneric
    -0.07
    ãĥŃãĥ¼
    -0.07
    irut
    -0.07
    ardu
    -0.07
    arer
    -0.07
    chaft
    -0.07
    arden
    -0.07
    dez
    -0.07
    ãĥ¼ãĥŃ
    -0.07
    POSITIVE LOGITS
     Bauer
    0.06
    ép
    0.06
    imit
    0.06
    RTC
    0.06
    yl
    0.06
    ne
    0.06
    ãĥĥãĤ¯ãĤ¹
    0.05
     Guar
    0.05
    798
    0.05
     Obl
    0.05
    Activations Density 0.005%

    No Known Activations