© 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. 60487
    Prev
    Next
    INDEX
    Explanations

    intensifiers, particularly variations of the word "very"

    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
     unw
    -0.07
    ÙĪارÙĩ
    -0.07
    isos
    -0.07
    agnet
    -0.06
    iros
    -0.06
    ajor
    -0.06
    noc
    -0.06
    amerate
    -0.06
    isan
    -0.06
    stice
    -0.06
    POSITIVE LOGITS
     soon
    0.07
    _skb
    0.07
     likely
    0.06
    egt
    0.06
    .qual
    0.06
    likely
    0.06
    onya
    0.06
    vik
    0.06
     wohl
    0.06
    _processors
    0.06
    Activations Density 0.020%

    No Known Activations