© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82401
    Prev
    Next
    INDEX
    Explanations

    instances of the word "By" that indicate authorship or attribution in a text

    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
    анÑĤаж
    -0.08
    اÙĨÚ¯
    -0.08
    umann
    -0.07
    Ø´ÙħاÙĦÛĮ
    -0.07
    iline
    -0.07
    yc
    -0.07
    irit
    -0.07
    ello
    -0.07
    angs
    -0.06
     BaÅŁkan
    -0.06
    POSITIVE LOGITS
    orning
    0.06
    ernes
    0.06
    .admin
    0.06
     admin
    0.06
     Exercise
    0.06
    ogg
    0.06
     exercise
    0.05
    dsp
    0.05
     BRAND
    0.05
    /admin
    0.05
    Activations Density 0.006%

    No Known Activations