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

    Neuronpedia

    APICircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5464
    Prev
    Next
    INDEX
    Explanations

    references to sports performance and statistics

    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
     OnTrigger
    -0.08
    connexion
    -0.07
     irresist
    -0.07
    å¶
    -0.07
    té
    -0.06
    .undefined
    -0.06
    gne
    -0.06
    orce
    -0.06
    ystems
    -0.06
    acker
    -0.06
    POSITIVE LOGITS
     losses
    0.08
     loss
    0.08
    apia
    0.07
     fortn
    0.07
     win
    0.07
     road
    0.07
     Loss
    0.07
     LOSS
    0.07
     Week
    0.07
     week
    0.07
    Activations Density 0.020%

    No Known Activations