© 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. 3839
    Prev
    Next
    INDEX
    Explanations

    references to television networks and shows

    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
    unte
    -0.08
    ulner
    -0.07
    åħ·
    -0.06
     mes
    -0.06
    å¼ĺ
    -0.06
    егоÑĢ
    -0.06
     radio
    -0.06
    ordion
    -0.06
    napshot
    -0.06
    ajor
    -0.06
    POSITIVE LOGITS
    iyi
    0.07
     network
    0.07
     programming
    0.07
     sister
    0.07
     Original
    0.07
    _logo
    0.06
    ision
    0.06
    .com
    0.06
    network
    0.06
    HD
    0.06
    Activations Density 0.021%

    No Known Activations