© 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. 85459
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility 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
    NECT
    -0.07
     Prob
    -0.07
     prob
    -0.06
     "[%
    -0.06
     circ
    -0.06
    ippet
    -0.06
    orman
    -0.06
    reme
    -0.06
     probably
    -0.06
    æĭŁ
    -0.06
    POSITIVE LOGITS
     Soon
    0.08
     soon
    0.08
    Soon
    0.07
    soon
    0.07
     solution
    0.07
    åºĥ
    0.07
     Cann
    0.07
    ril
    0.06
    solution
    0.06
    690
    0.06
    Activations Density 0.025%

    No Known Activations