© 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 EvalsExportsinterp-engineNEWAPI 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. 104650
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "few" and its variations

    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
     dál
    -0.07
    zon
    -0.07
    aml
    -0.06
    umer
    -0.06
    laz
    -0.06
    stice
    -0.06
    forge
    -0.06
    chers
    -0.06
    asser
    -0.06
    ï¼
    -0.05
    POSITIVE LOGITS
     ever
    0.08
    -ever
    0.07
    /no
    0.07
     other
    0.07
    ÙĮ
    0.07
     EVER
    0.07
     doubt
    0.07
    ALLERY
    0.07
    theless
    0.07
    ,No
    0.07
    Activations Density 0.005%

    No Known Activations