© 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. 9-LLAMASCOPE-RES-131K
    11. 95603
    Prev
    Next
    INDEX
    Explanations

    phrases or structures indicating future events or significant change

    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
    apper
    -0.08
    amburger
    -0.07
    aylight
    -0.07
    OffsetTable
    -0.07
     overd
    -0.07
     gras
    -0.06
    Fade
    -0.06
    herits
    -0.06
    ToSelector
    -0.06
    APPER
    -0.06
    POSITIVE LOGITS
    .dsl
    0.06
    ç«Ł
    0.06
     змÑĸ
    0.06
    lass
    0.06
    令
    0.05
    ethe
    0.05
    Æ°a
    0.05
    egree
    0.05
     Bott
    0.05
    sembly
    0.05
    Activations Density 0.018%

    No Known Activations