© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75119
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives describing sizes, speeds, and quantities

    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
    çŁ¢
    -0.07
    ENO
    -0.07
    Rare
    -0.07
    eyin
    -0.06
    ibold
    -0.06
    uchs
    -0.06
    çĽĸ
    -0.06
    illin
    -0.06
    Ñīи
    -0.06
    utenberg
    -0.06
    POSITIVE LOGITS
    arel
    0.08
    inki
    0.06
    ulos
    0.06
    andon
    0.06
     ancest
    0.06
     erh
    0.06
    iec
    0.06
     Rib
    0.06
    tera
    0.06
    adow
    0.06
    Activations Density 0.007%

    No Known Activations