© 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. 73743
    Prev
    Next
    INDEX
    Explanations

    code-related phrases and functions within a programming context

    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
    ÃĸL
    -0.06
    å®ĭä½ĵ
    -0.06
    CHANT
    -0.06
    ousse
    -0.06
    .xtext
    -0.06
    asper
    -0.06
    ovat
    -0.06
    åĽ£
    -0.06
    Å¡et
    -0.06
    ponsive
    -0.06
    POSITIVE LOGITS
     stack
    0.08
    æł
    0.08
     stacking
    0.07
     Stack
    0.07
     Route
    0.07
    erk
    0.07
    Stack
    0.07
    _stack
    0.07
     Pages
    0.07
     STACK
    0.07
    Activations Density 0.025%

    No Known Activations