© 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. 95568
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility, necessity, and conditionals

    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
    κοÏħ
    -0.06
    appe
    -0.06
     is
    -0.06
    asca
    -0.06
    eph
    -0.06
    ira
    -0.06
     Eisen
    -0.06
    .Utils
    -0.05
     Happ
    -0.05
    ity
    -0.05
    POSITIVE LOGITS
    've
    0.10
    ’ve
    0.10
    äºĨä¸Ģ
    0.10
     vardı
    0.09
     Äijã
    0.08
     hät
    0.08
     hätte
    0.08
     haber
    0.08
     was
    0.08
     telah
    0.08
    Activations Density 0.029%

    No Known Activations