© 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. 17-LLAMASCOPE-RES-131K
    11. 87120
    Prev
    Next
    INDEX
    Explanations

    numerical data related to beverage sales and market trends

    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
    ]âĢı
    -0.07
    redo
    -0.07
    mdi
    -0.06
    hoff
    -0.06
     Savage
    -0.06
    oon
    -0.06
    inality
    -0.06
    rane
    -0.06
    份
    -0.06
    onen
    -0.05
    POSITIVE LOGITS
    udio
    0.07
    едини
    0.06
    .Theme
    0.06
     ÙĥÙĪر
    0.06
     Bien
    0.06
    å¼¹
    0.06
    ROTO
    0.06
     plurality
    0.06
    _opcode
    0.06
    ic
    0.06
    Activations Density 0.010%

    No Known Activations