© 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. 93009
    Prev
    Next
    INDEX
    Explanations

    words related to conditional statements or expectations

    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
    rons
    -0.07
    amil
    -0.07
    hek
    -0.06
    eÄį
    -0.06
    405
    -0.06
    eping
    -0.06
    Xml
    -0.06
    mag
    -0.06
    zet
    -0.06
    zo
    -0.06
    POSITIVE LOGITS
    STANCE
    0.06
    (æ°´
    0.06
    arged
    0.06
    UMB
    0.06
    orra
    0.06
    stant
    0.06
    éric
    0.06
    ÙĦÛĮس
    0.06
     bä
    0.06
    atis
    0.06
    Activations Density 0.000%

    No Known Activations