© 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. 119438
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility, necessity, or potential outcomes

    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
    еÑĢк
    -0.07
     dint
    -0.07
    otu
    -0.07
    imet
    -0.06
    ÏģÏİν
    -0.06
    âķĹ
    -0.06
    chter
    -0.06
    .aspx
    -0.06
    morph
    -0.06
    fik
    -0.06
    POSITIVE LOGITS
    steder
    0.07
    ente
    0.07
    141
    0.07
     therefore
    0.07
    chap
    0.07
    InputDialog
    0.06
    	TokenName
    0.06
    985
    0.06
    urnal
    0.06
     potentially
    0.06
    Activations Density 0.078%

    No Known Activations