© 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. 76125
    Prev
    Next
    INDEX
    Explanations

    the word "furthermore" and related continuative phrases

    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
    ing
    -0.07
    tte
    -0.07
     æ¤
    -0.07
    ipl
    -0.07
    anou
    -0.07
    rung
    -0.06
    ific
    -0.06
    153
    -0.06
    ipping
    -0.06
    ties
    -0.06
    POSITIVE LOGITS
    PHA
    0.07
    ,
    0.06
    asley
    0.06
    elic
    0.06
     Ele
    0.06
     ÙģØ¥ÙĨ
    0.06
    eten
    0.06
    SizePolicy
    0.06
    anton
    0.06
    hangi
    0.06
    Activations Density 0.006%

    No Known Activations