© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104984
    Prev
    Next
    INDEX
    Explanations

    references to storytelling elements and narrative devices

    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
    arger
    -0.07
     Åŀu
    -0.07
    /tags
    -0.06
    unma
    -0.06
    iny
    -0.06
    åIJī
    -0.06
    reeNode
    -0.06
     McCl
    -0.06
     tuy
    -0.06
    é¨
    -0.06
    POSITIVE LOGITS
     concerned
    0.11
    (s
    0.09
     itself
    0.08
     selected
    0.07
     chosen
    0.07
    åıĬåħ¶
    0.07
    chosen
    0.07
     or
    0.06
    seau
    0.06
    ous
    0.06
    Activations Density 0.105%

    No Known Activations