© 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. 15722
    Prev
    Next
    INDEX
    Explanations

    phrases indicating division or categorization into groups

    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
    immel
    -0.10
     nues
    -0.08
    اÙĩد
    -0.08
    loh
    -0.07
    jam
    -0.07
    åįģåħ«
    -0.07
    nodeName
    -0.07
    LÄ°
    -0.07
    ngo
    -0.07
    _restrict
    -0.07
    POSITIVE LOGITS
     two
    0.13
     three
    0.10
    two
    0.09
     thirds
    0.08
     separate
    0.08
     several
    0.08
    èĭ¥
    0.08
    两个
    0.07
     four
    0.07
    _two
    0.07
    Activations Density 0.016%

    No Known Activations