© 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. 17-LLAMASCOPE-RES-131K
    11. 128032
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords in code snippets

    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
    vent
    -0.07
    ahan
    -0.07
    opyright
    -0.06
    toHave
    -0.06
    ross
    -0.06
    werk
    -0.06
     strerror
    -0.06
    (getClass
    -0.06
    /apache
    -0.06
    sep
    -0.06
    POSITIVE LOGITS
    =true
    0.09
     |=
    0.09
     TRUE
    0.09
    =True
    0.08
     True
    0.07
     =
    0.07
    True
    0.07
    TRUE
    0.07
     true
    0.07
    884
    0.07
    Activations Density 0.010%

    No Known Activations