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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96148
    Prev
    Next
    INDEX
    Explanations

    references to contracts and monetary values in professional sports

    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
    iere
    -0.07
    .har
    -0.06
    S
    -0.06
    quirer
    -0.06
    archy
    -0.06
    cha
    -0.05
    ÑĢÑĸв
    -0.05
    .ma
    -0.05
     ib
    -0.05
    errer
    -0.05
    POSITIVE LOGITS
    ycastle
    0.07
    <quote
    0.07
     Lair
    0.07
    esco
    0.07
    :NSLocalizedString
    0.07
     калÑĮ
    0.07
    ahy
    0.06
     éĩĮ
    0.06
     Animalia
    0.06
    uyên
    0.06
    Activations Density 0.023%

    No Known Activations