© 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. 117237
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "package" 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
    arat
    -0.07
    avenport
    -0.07
    å¾½
    -0.06
    ç¢İ
    -0.06
    arah
    -0.06
    emer
    -0.06
    ihan
    -0.06
    avadoc
    -0.06
    aversable
    -0.06
    ascus
    -0.06
    POSITIVE LOGITS
     åī
    0.07
    ream
    0.06
    anos
    0.06
    วà¸Ļ
    0.06
    -addon
    0.06
    ogne
    0.06
     Bord
    0.06
    addtogroup
    0.06
     ausge
    0.05
    alsa
    0.05
    Activations Density 0.001%

    No Known Activations