© 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. 83122
    Prev
    Next
    INDEX
    Explanations

    words that refer to risks or challenges

    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
     ëı
    -0.07
    reau
    -0.07
    aqu
    -0.06
    cke
    -0.06
     Latina
    -0.06
     handwriting
    -0.06
    whose
    -0.06
    inite
    -0.06
    ular
    -0.06
    ushi
    -0.06
    POSITIVE LOGITS
    swer
    0.08
     تÙĪسط
    0.08
     by
    0.07
    921
    0.07
     oleh
    0.07
    âl
    0.06
    yon
    0.06
    937
    0.06
    orny
    0.06
    درس
    0.06
    Activations Density 0.016%

    No Known Activations