© 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. 88049
    Prev
    Next
    INDEX
    Explanations

    key elements related to character development and emotional stakes in storytelling

    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
    IFO
    -0.08
     ontvangst
    -0.07
    ebra
    -0.07
    ctp
    -0.07
     /*#__
    -0.07
    aler
    -0.07
    rsa
    -0.07
    rahim
    -0.07
    metros
    -0.07
    orsi
    -0.06
    POSITIVE LOGITS
     action
    0.07
    ç©
    0.06
     Character
    0.06
     tang
    0.06
    action
    0.06
    /ch
    0.06
     Action
    0.06
     Lester
    0.06
    _busy
    0.06
     midd
    0.06
    Activations Density 0.007%

    No Known Activations