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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28180
    Prev
    Next
    INDEX
    Explanations

    mentions of historical dates and 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
    legen
    -0.07
    ews
    -0.07
    eldo
    -0.07
    длÑı
    -0.06
    utow
    -0.06
    agra
    -0.06
    ety
    -0.06
    VOID
    -0.06
    ektör
    -0.06
     antagon
    -0.06
    POSITIVE LOGITS
    esti
    0.06
    319
    0.06
    ãĥ«ãĤ¯
    0.06
    à¥Ģà¤ķ
    0.06
     ...
    0.06
     neither
    0.06
    ÑģÑĤи
    0.05
    ATS
    0.05
     ActionType
    0.05
    embre
    0.05
    Activations Density 0.061%

    No Known Activations