© 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. 71778
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to historical narratives and characters

    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
    ville
    -0.07
    elden
    -0.07
     hend
    -0.07
    imbus
    -0.07
    rimon
    -0.07
     Nec
    -0.06
    ediator
    -0.06
    _Cmd
    -0.06
    udget
    -0.06
     Kosten
    -0.06
    POSITIVE LOGITS
     rug
    0.06
     birth
    0.06
     dj
    0.06
     ÑģлÑĥÑħ
    0.06
    wagon
    0.06
     indent
    0.06
    nio
    0.06
     Assassin
    0.05
     bir
    0.05
    anio
    0.05
    Activations Density 0.021%

    No Known Activations