© 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. 3703
    Prev
    Next
    INDEX
    Explanations

    matchups between teams or competitors in sporting events

    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
    ิà¸ķย
    -0.07
    kola
    -0.07
    маз
    -0.06
    ghan
    -0.06
    graf
    -0.06
    ÑĪин
    -0.06
    ÃŃl
    -0.06
    ius
    -0.06
    nerg
    -0.06
    anton
    -0.06
    POSITIVE LOGITS
    /of
    0.08
    antro
    0.07
    raquo
    0.07
    lisi
    0.07
    ulumi
    0.07
    Та
    0.07
    utterstock
    0.06
    ÐĴÑĸн
    0.06
    'yi
    0.06
    ï¸
    0.06
    Activations Density 0.012%

    No Known Activations