© 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 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. 17-LLAMASCOPE-RES-131K
    11. 76440
    Prev
    Next
    INDEX
    Explanations

    elements or components related to technology specifications

    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
    lection
    -0.07
    282
    -0.06
     th
    -0.06
     Klopp
    -0.06
    haus
    -0.06
    azel
    -0.06
    06
    -0.06
     v
    -0.06
    ...
    -0.06
    hurst
    -0.06
    POSITIVE LOGITS
     wides
    0.08
     京
    0.08
    chio
    0.08
    hek
    0.08
    à¹ģส
    0.07
     ìłĪ
    0.07
    #ab
    0.07
    ÙĤÙĬ
    0.07
    ets
    0.07
    ãĥĨãĤ£
    0.07
    Activations Density 0.002%

    No Known Activations