Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74956
    Prev
    Next
    INDEX
    Explanations

    elements related to web design and coding features

    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
    formats
    -0.10
    /umd
    -0.08
    gis
    -0.08
    .ObjectMeta
    -0.07
    cams
    -0.07
     RequestMethod
    -0.07
    elman
    -0.07
    ÙĤÙħ
    -0.07
    ledon
    -0.07
    :UIAlert
    -0.07
    POSITIVE LOGITS
     Theme
    0.07
     included
    0.07
     
    0.07
     theme
    0.06
     feature
    0.06
     built
    0.06
     ve
    0.06
     Vega
    0.06
     Morris
    0.06
     News
    0.05
    Activations Density 0.006%

    No Known Activations