© 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 EvalsExportsAPI 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. 118769
    Prev
    Next
    INDEX
    Explanations

    phrases indicating engagement or direction in conversation

    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
    around
    -0.07
    stitute
    -0.06
    zim
    -0.06
    ctrine
    -0.06
    eri
    -0.06
    /repos
    -0.06
    1
    -0.06
    emi
    -0.06
    ble
    -0.06
     illicit
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    uales
    0.07
    vail
    0.07
     pen
    0.07
    obar
    0.07
    Ñİк
    0.07
    .until
    0.06
    tsy
    0.06
    Äįen
    0.06
    (=)
    0.06
    Activations Density 0.012%

    No Known Activations