© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94103
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or possibility

    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
    .Library
    -0.08
    ãĥĬãĥ¼
    -0.06
    ิà¸ŀ
    -0.06
    dk
    -0.06
    ادات
    -0.06
    .library
    -0.06
    .Notify
    -0.06
    обов
    -0.06
    zier
    -0.06
     unsus
    -0.06
    POSITIVE LOGITS
     possibly
    0.07
    uckle
    0.07
     Possibly
    0.07
     afford
    0.06
    ot
    0.06
     possibility
    0.06
    opic
    0.06
    ucks
    0.06
    anker
    0.06
    als
    0.06
    Activations Density 0.080%

    No Known Activations