© 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 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. 57435
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals or entities in a narrative context

    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
    Ư
    -0.08
    à¹ģม
    -0.08
    cente
    -0.08
    ÑĢим
    -0.08
    ë¹Ħ
    -0.08
    ehler
    -0.08
    oreach
    -0.08
    ılıp
    -0.08
    inely
    -0.08
     PureComponent
    -0.08
    POSITIVE LOGITS
     himself
    0.09
     former
    0.08
     man
    0.08
     bes
    0.08
     er
    0.07
     boy
    0.07
     his
    0.06
     icon
    0.06
     Former
    0.06
     native
    0.06
    Activations Density 0.062%

    No Known Activations