© 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. 15765
    Prev
    Next
    INDEX
    Explanations

    discussions about storytelling and the process of narrative creation

    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
    roman
    -0.06
    à¸ī
    -0.06
    nost
    -0.06
    alez
    -0.06
    onet
    -0.06
    Ĺ
    -0.06
    aut
    -0.05
     getArguments
    -0.05
     Bowman
    -0.05
    utra
    -0.05
    POSITIVE LOGITS
    /moment
    0.08
    hlen
    0.08
    ÅĽnie
    0.08
    ë§Ŀ
    0.07
    licative
    0.06
    alars
    0.06
    ernals
    0.06
    iguiente
    0.06
    //------------------------------------------------------------------------------↵↵
    0.06
    chwitz
    0.06
    Activations Density 0.004%

    No Known Activations