© 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. 57508
    Prev
    Next
    INDEX
    Explanations

    programming-related actions and functions

    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
    abama
    -0.07
    ento
    -0.07
    olut
    -0.06
    ож
    -0.06
    ForObject
    -0.06
    luent
    -0.06
    WithDuration
    -0.06
    ائر
    -0.06
    ewitness
    -0.06
    swer
    -0.06
    POSITIVE LOGITS
    egin
    0.06
    gre
    0.06
    oder
    0.06
     vale
    0.06
    ify
    0.06
    ayıp
    0.06
    <decltype
    0.06
    able
    0.06
    oned
    0.06
     hindsight
    0.06
    Activations Density 0.149%

    No Known Activations