© 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. 60909
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    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
     unless
    -0.07
    asa
    -0.07
    bara
    -0.07
    unless
    -0.06
    _FE
    -0.06
    Ñĥже
    -0.06
    ald
    -0.06
    rade
    -0.06
    éĻ¤
    -0.06
    boa
    -0.06
    POSITIVE LOGITS
     behalf
    0.07
     suá»ijt
    0.07
     throughout
    0.07
    CTS
    0.07
    elm
    0.07
    anging
    0.07
     SHARES
    0.06
    عاÙĨ
    0.06
    	throws
    0.06
     tão
    0.06
    Activations Density 0.056%

    No Known Activations