© 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. 127346
    Prev
    Next
    INDEX
    Explanations

    mentions of specific months, particularly focusing on October and November

    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
    anim
    -0.07
    ENDING
    -0.07
    ending
    -0.06
     kims
    -0.06
    ember
    -0.06
     Nash
    -0.06
    wand
    -0.06
    923
    -0.06
    edia
    -0.06
     Bernstein
    -0.06
    POSITIVE LOGITS
    odial
    0.07
    uesta
    0.07
    isque
    0.07
    ayload
    0.07
    malink
    0.07
    pository
    0.06
    /stdc
    0.06
    amac
    0.06
    _<?
    0.06
    aye
    0.06
    Activations Density 0.010%

    No Known Activations