© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76937
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in expressing possibility or necessity

    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
    -lnd
    -0.08
    redient
    -0.07
    owel
    -0.07
    .scalablytyped
    -0.07
    senal
    -0.07
    UAGE
    -0.07
    ajÄħc
    -0.07
    racat
    -0.07
    oplevel
    -0.07
    ısıt
    -0.07
    POSITIVE LOGITS
    AILS
    0.06
    Ïģκ
    0.06
     Göz
    0.05
     kapit
    0.05
     either
    0.05
     Faul
    0.05
     sho
    0.05
     often
    0.05
     pseud
    0.05
     set
    0.05
    Activations Density 0.025%

    No Known Activations