© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 15747
    Prev
    Next
    INDEX
    Explanations

    key events and statistics related to American football

    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
    Macro
    -0.07
    intree
    -0.07
    gue
    -0.06
    .slim
    -0.06
    chedulers
    -0.06
    _argument
    -0.06
    riday
    -0.06
    ิà¸ļ
    -0.06
    urge
    -0.06
    .mvc
    -0.06
    POSITIVE LOGITS
     Kick
    0.08
     kicks
    0.07
     kick
    0.07
     Magnus
    0.07
    Kick
    0.07
     Strand
    0.06
     touch
    0.06
     fair
    0.06
     entr
    0.06
    uje
    0.06
    Activations Density 0.012%

    No Known Activations