© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104377
    Prev
    Next
    INDEX
    Explanations

    references to economic professionals and their statements

    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
    ocol
    -0.06
    еÑĢалÑĮ
    -0.06
    Æ°á»
    -0.06
    uras
    -0.06
    егоÑĢ
    -0.06
     ÑĤÑĢÑĥ
    -0.06
    upid
    -0.06
    oken
    -0.06
    ubo
    -0.06
    abilia
    -0.06
    POSITIVE LOGITS
    licer
    0.07
    Macro
    0.07
     macro
    0.07
    LIB
    0.06
     charts
    0.06
    ]|[
    0.06
     Macro
    0.06
     Kang
    0.06
    macro
    0.06
    ormsg
    0.06
    Activations Density 0.012%

    No Known Activations