© 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. 87100
    Prev
    Next
    INDEX
    Explanations

    phrases indicating obligation 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
    ilde
    -0.08
    rch
    -0.08
    ãģłãģĭãĤī
    -0.07
    Äĥm
    -0.07
    auses
    -0.07
    arendra
    -0.07
    .ver
    -0.07
    ebin
    -0.07
    raquo
    -0.07
    aveled
    -0.07
    POSITIVE LOGITS
     sometimes
    0.07
     sooner
    0.07
     often
    0.07
     familiar
    0.07
    ine
    0.06
    menin
    0.06
    yl
    0.06
    sometimes
    0.06
     inev
    0.06
     need
    0.06
    Activations Density 0.045%

    No Known Activations