© 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. 40394
    Prev
    Next
    INDEX
    Explanations

    references to comparison or evaluation of options

    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
    icks
    -0.06
    гал
    -0.06
    cept
    -0.06
    uring
    -0.06
    jang
    -0.06
    hazi
    -0.06
    outu
    -0.06
    aking
    -0.06
     Howe
    -0.06
    igg
    -0.06
    POSITIVE LOGITS
     parties
    0.10
     Parties
    0.10
     party
    0.09
     halves
    0.09
     sides
    0.09
    æĸ¹
    0.08
     sexes
    0.08
    half
    0.08
     two
    0.08
    ãģ¡ãĤī
    0.08
    Activations Density 0.144%

    No Known Activations