© 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. 108191
    Prev
    Next
    INDEX
    Explanations

    the frequency and significance of the word "most" and its variations in contexts describing quantity or prevalence

    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
    ury
    -0.07
    loquent
    -0.07
    ĥ
    -0.06
    Seat
    -0.06
    stand
    -0.06
    Withdraw
    -0.06
    bose
    -0.06
    insky
    -0.06
     magnitude
    -0.06
     Alloc
    -0.06
    POSITIVE LOGITS
     of
    0.11
    θοÏĤ
    0.07
    ä¸Ģ页
    0.07
    OfClass
    0.06
    OfFile
    0.06
    ãĥ¼ãĥŀ
    0.06
    .of
    0.06
    utsch
    0.06
    villa
    0.06
    oward
    0.06
    Activations Density 0.002%

    No Known Activations