© 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. 125547
    Prev
    Next
    INDEX
    Explanations

    mentions of dates and numbers related to events

    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
    OE
    -0.07
    signals
    -0.07
    oops
    -0.07
    patches
    -0.07
    reh
    -0.07
    leo
    -0.07
     blank
    -0.07
    ¼åIJĪ
    -0.07
     Signals
    -0.07
    blank
    -0.07
    POSITIVE LOGITS
    elay
    0.06
     setC
    0.06
     GPI
    0.06
     mate
    0.06
     Shepherd
    0.06
    alsy
    0.06
    arend
    0.06
     Mate
    0.06
     Kut
    0.06
     execut
    0.05
    Activations Density 0.001%

    No Known Activations