© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57692
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant outcomes or events in sports contexts

    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
    ething
    -0.06
    ighth
    -0.06
    /downloads
    -0.06
    é
    -0.06
    rieve
    -0.06
     separately
    -0.05
     unlike
    -0.05
    haar
    -0.05
    ardon
    -0.05
    å±Ĭ
    -0.05
    POSITIVE LOGITS
    ingo
    0.08
    .MixedReality
    0.07
    riad
    0.07
    ãĤ¹ãĤ¯
    0.07
    ombat
    0.07
    itag
    0.06
    allax
    0.06
    iner
    0.06
     vic
    0.06
     RelayCommand
    0.06
    Activations Density 0.010%

    No Known Activations