© 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. 84654
    Prev
    Next
    INDEX
    Explanations

    references to scriptwriting and film production

    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
    icious
    -0.08
    gom
    -0.07
    empor
    -0.07
    æĺĩ
    -0.07
    ıs
    -0.07
    ",__
    -0.07
    ensex
    -0.07
    aign
    -0.06
     annonces
    -0.06
    /dir
    -0.06
    POSITIVE LOGITS
     ready
    0.15
     already
    0.15
    ready
    0.14
    already
    0.13
     READY
    0.13
    Already
    0.13
     Already
    0.12
     Ready
    0.12
    READY
    0.10
    å·²ç»ı
    0.10
    Activations Density 0.032%

    No Known Activations