© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103683
    Prev
    Next
    INDEX
    Explanations

    references to data structures, particularly 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
    ãĢħ
    -0.08
     latter
    -0.08
    ebek
    -0.07
    ampa
    -0.07
    bourne
    -0.07
    allo
    -0.07
    اپ
    -0.07
    aly
    -0.06
    DATED
    -0.06
    oooo
    -0.06
    POSITIVE LOGITS
    urator
    0.09
    /-
    0.08
    enticator
    0.07
    ìĿ´íĦ°
    0.07
    ibraries
    0.07
    âĢĮسÛĮ
    0.07
    oled
    0.06
    @brief
    0.06
    ÙĪاء
    0.06
    raries
    0.06
    Activations Density 0.122%

    No Known Activations