© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93369
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or inability

    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
    lod
    -0.09
    asio
    -0.08
    .scalablytyped
    -0.08
    á»ı
    -0.07
    asje
    -0.07
    eled
    -0.07
    combe
    -0.07
    nist
    -0.07
    adb
    -0.07
    .gameserver
    -0.07
    POSITIVE LOGITS
    nt
    0.11
    ÅĽmy
    0.09
    ed
    0.09
    've
    0.09
     originally
    0.09
    ’ve
    0.08
    a
    0.08
     latter
    0.08
    ëĬĶ
    0.08
    gies
    0.08
    Activations Density 0.071%

    No Known Activations