© 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. 94633
    Prev
    Next
    INDEX
    Explanations

    references to semiconductor production and related technology

    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
    selectAll
    -0.06
    елÑĮзÑı
    -0.06
     Sext
    -0.06
     ctype
    -0.06
    à¥Ģà¤ıस
    -0.06
    ordova
    -0.06
    hu
    -0.06
    -percent
    -0.05
    .SelectedItems
    -0.05
     bonded
    -0.05
    POSITIVE LOGITS
     rival
    0.07
    rente
    0.07
    erd
    0.06
    mens
    0.06
     bet
    0.06
    ecast
    0.06
    anic
    0.06
    иÑĨин
    0.06
     interpre
    0.06
    zyst
    0.06
    Activations Density 0.026%

    No Known Activations