© 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. 15-LLAMASCOPE-RES-131K
    11. 89624
    Prev
    Next
    INDEX
    Explanations

    references to notable figures in English literature and culture

    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
    akis
    -0.07
    ttp
    -0.07
    illard
    -0.06
    tdown
    -0.06
     Liter
    -0.06
     archival
    -0.05
     Resist
    -0.05
     McKenzie
    -0.05
     Esk
    -0.05
    archical
    -0.05
    POSITIVE LOGITS
    #echo
    0.07
    vyk
    0.07
    Tit
    0.07
    INET
    0.07
    _pref
    0.07
     Volume
    0.07
    à¸Ļà¹ĥà¸Ī
    0.07
     DÄĽ
    0.07
    /qt
    0.07
    weis
    0.07
    Activations Density 0.026%

    No Known Activations