© 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. 56013
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases that imply obligation or moral duty

    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
    ãĥ©ãĤ¤ãĥ³
    -0.07
     borderBottom
    -0.07
    rocket
    -0.07
    ritz
    -0.07
    .DEFINE
    -0.07
    Rocket
    -0.07
    sip
    -0.07
    ãģ¾ãĤĭ
    -0.07
    λεκ
    -0.06
    tk
    -0.06
    POSITIVE LOGITS
    ovy
    0.06
    殿
    0.06
    669
    0.06
    ñas
    0.06
    lsen
    0.06
    resa
    0.06
    issor
    0.06
     Sheep
    0.06
    erti
    0.05
    agram
    0.05
    Activations Density 0.002%

    No Known Activations