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. 96046
    Prev
    Next
    INDEX
    Explanations

    references to athletics and athletic programs

    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
    ophone
    -0.07
    æ°ı
    -0.06
     hyp
    -0.06
    bies
    -0.06
     exc
    -0.06
    616
    -0.06
     sup
    -0.06
    pires
    -0.06
    nette
    -0.06
    ary
    -0.05
    POSITIVE LOGITS
    lander
    0.07
    olson
    0.07
    اÙĦØ©
    0.07
    rx
    0.07
    viso
    0.07
    umas
    0.06
    raft
    0.06
    uttle
    0.06
    andro
    0.06
    QRS
    0.06
    Activations Density 0.006%

    No Known Activations