© 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. 56526
    Prev
    Next
    INDEX
    Explanations

    actions related to online processes and content creation

    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
     equipments
    -0.08
    osg
    -0.07
     atleast
    -0.07
    âijł
    -0.06
    -âĢIJ
    -0.06
     âĢª
    -0.06
     UsersController
    -0.06
    ixels
    -0.06
    linger
    -0.06
     lenght
    -0.06
    POSITIVE LOGITS
    ä¾
    0.07
    https
    0.07
    202
    0.07
     Valor
    0.06
    inh
    0.06
     Ches
    0.06
     Whale
    0.06
     policym
    0.06
    ðŁ
    0.06
     mainly
    0.06
    Activations Density 0.003%

    No Known Activations