© 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. 15-LLAMASCOPE-RES-131K
    11. 103395
    Prev
    Next
    INDEX
    Explanations

    defensive actions and significant plays 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
    инок
    -0.08
    rière
    -0.07
    IGHL
    -0.07
    کاÙĨ
    -0.07
    USTOM
    -0.07
    адÑĥ
    -0.07
    anova
    -0.07
    æ®
    -0.07
     pii
    -0.07
    anke
    -0.07
    POSITIVE LOGITS
    l
    0.07
     Za
    0.06
    uch
    0.06
    omo
    0.05
     directly
    0.05
     Mark
    0.05
     Shah
    0.05
    lements
    0.05
     Grant
    0.05
    ohn
    0.05
    Activations Density 0.008%

    No Known Activations