© 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. 85527
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence fragments

    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
    ibold
    -0.07
    Ñİн
    -0.07
    eland
    -0.07
    ัà¸Ļà¸ķ
    -0.07
    åĶ
    -0.06
     Pension
    -0.06
     Ø®ÙĦ
    -0.06
    ignon
    -0.06
    utin
    -0.06
    ferred
    -0.06
    POSITIVE LOGITS
     otherwise
    0.09
     Otherwise
    0.08
     or
    0.07
    Alternatively
    0.07
    emale
    0.07
    æĪĸèĢħ
    0.07
    iku
    0.07
    else
    0.06
    otherwise
    0.06
    æ¯ķ
    0.06
    Activations Density 0.074%

    No Known Activations