© 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. 88923
    Prev
    Next
    INDEX
    Explanations

    content related to notable publications and authors in literature

    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
    ÐķТ
    -0.06
    Ø´ÙħاÙĦÛĮ
    -0.06
    æľ
    -0.06
    .StackTrace
    -0.06
    196
    -0.06
    ãĢ
    -0.06
    1
    -0.06
    enstein
    -0.06
    &eacute
    -0.06
    -м
    -0.06
    POSITIVE LOGITS
    202
    0.22
    201
    0.21
    Û²Û°Û±
    0.14
    Û²Û°Û²
    0.13
     Covid
    0.10
     COVID
    0.10
     covid
    0.09
     https
    0.09
    https
    0.09
    _https
    0.09
    Activations Density 0.078%

    No Known Activations