© 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. 83933
    Prev
    Next
    INDEX
    Explanations

    instances of criminal activity or deceitful behavior

    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
    วà¸ģ
    -0.08
    ivent
    -0.07
     helicopt
    -0.07
    orex
    -0.07
    ê´
    -0.07
    ãĥ³ãĥĢ
    -0.07
    setFlash
    -0.07
    ìĭ¸
    -0.07
     ÑĨÑĸл
    -0.07
    eking
    -0.06
    POSITIVE LOGITS
    0.09
     ðŁ
    0.06
    SB
    0.06
    0.06
    ibold
    0.06
     neighbors
    0.06
     ditch
    0.06
    ugar
    0.06
     state
    0.06
     neighbor
    0.06
    Activations Density 0.004%

    No Known Activations