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

    Neuronpedia

    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. 124912
    Prev
    Next
    INDEX
    Explanations

    content related to instructional or editorial references, particularly about reading or accessing further information

    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
    apat
    -0.06
    æŁĦ
    -0.06
    ilee
    -0.05
    æ²¢
    -0.05
     Curtis
    -0.05
     mö
    -0.05
     Appendix
    -0.05
     appendix
    -0.05
     cus
    -0.05
    inee
    -0.05
    POSITIVE LOGITS
     previous
    0.10
    previous
    0.09
    .previous
    0.09
    Previous
    0.09
    (previous
    0.08
     Previous
    0.08
     earlier
    0.08
    belum
    0.08
    scribe
    0.07
    _previous
    0.07
    Activations Density 0.014%

    No Known Activations