© 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. 77223
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their attributes

    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
     Fuji
    -0.07
    ParameterValue
    -0.06
    Ñī
    -0.06
    ICLE
    -0.06
    æĭħå½ĵ
    -0.06
    ekl
    -0.06
    Äĥng
    -0.06
    ÙĥÙĪÙĨ
    -0.06
    ewan
    -0.06
    _fb
    -0.06
    POSITIVE LOGITS
     header
    0.14
     headers
    0.13
    header
    0.12
    headers
    0.12
     Header
    0.12
    Header
    0.12
    -header
    0.11
    _header
    0.11
     headings
    0.10
     row
    0.10
    Activations Density 0.041%

    No Known Activations