© 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. 39670
    Prev
    Next
    INDEX
    Explanations

    the phrase "by" followed by impactful actions or descriptions that imply causation or agency

    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
    ами
    -0.07
    otts
    -0.07
    ught
    -0.06
    rip
    -0.06
    lest
    -0.06
    ÙİÙĤ
    -0.06
    flags
    -0.05
    /or
    -0.05
    ping
    -0.05
    ivation
    -0.05
    POSITIVE LOGITS
    alet
    0.07
    538
    0.07
    ť
    0.07
    ä¿
    0.07
    ehir
    0.07
     contrast
    0.07
    waters
    0.07
    ramid
    0.06
    enth
    0.06
    با
    0.06
    Activations Density 0.013%

    No Known Activations