© 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. 93590
    Prev
    Next
    INDEX
    Explanations

    names and titles related to individuals in the context of achievements and roles

    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
     Ballard
    -0.07
    apon
    -0.07
    onth
    -0.07
    aban
    -0.06
    .Tool
    -0.06
    SMART
    -0.06
     Madden
    -0.06
    èµĸ
    -0.06
    mani
    -0.06
    athi
    -0.06
    POSITIVE LOGITS
    essen
    0.07
    APPER
    0.07
     pau
    0.07
    ANJI
    0.07
    UGIN
    0.07
    iyim
    0.06
    äft
    0.06
    omm
    0.06
    PEND
    0.06
    «ĺ
    0.06
    Activations Density 0.007%

    No Known Activations