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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 96061
    Prev
    Next
    INDEX
    Explanations

    references to injuries and rehabilitation in athletes

    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
    ina
    -0.07
    cca
    -0.06
    tica
    -0.06
    161
    -0.06
    Coach
    -0.06
    ekler
    -0.05
    isci
    -0.05
    lm
    -0.05
    cri
    -0.05
     prompt
    -0.05
    POSITIVE LOGITS
    atever
    0.07
     subjective
    0.07
    GenerationStrategy
    0.07
    uze
    0.07
    isch
    0.06
    à¤Ĥà¤ľ
    0.06
    .Tool
    0.06
    SHA
    0.06
    GuidId
    0.06
    lıģına
    0.06
    Activations Density 0.134%

    No Known Activations