© 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. 54840
    Prev
    Next
    INDEX
    Explanations

    instances of stack trace or error reporting in programming 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
    ibold
    -0.07
    strtolower
    -0.07
    lap
    -0.07
    assage
    -0.06
    ạc
    -0.06
    ãģ£ãģ¡
    -0.06
     EGL
    -0.06
    жÑĥ
    -0.06
    @brief
    -0.06
    iros
    -0.06
    POSITIVE LOGITS
    qrt
    0.07
     Vance
    0.07
    .quick
    0.06
    گراÙĨ
    0.06
    IZER
    0.06
    oq
    0.06
     Paladin
    0.06
    699
    0.06
    953
    0.05
     Humph
    0.05
    Activations Density 0.001%

    No Known Activations