© 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. 87537
    Prev
    Next
    INDEX
    Explanations

    concepts relating to mathematical optimization and eigenvalue problems

    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
     quick
    -0.08
    lemn
    -0.06
    ool
    -0.06
    stride
    -0.06
    shal
    -0.06
    çħ
    -0.06
     comple
    -0.06
     guaranteed
    -0.06
     RU
    -0.06
     Fool
    -0.06
    POSITIVE LOGITS
    oji
    0.09
    #
    0.08
    жд
    0.07
    .cljs
    0.07
    OfString
    0.07
    Ñĩин
    0.07
    ACKET
    0.07
    .bio
    0.07
    .CommandType
    0.07
    å¯Į
    0.07
    Activations Density 0.092%

    No Known Activations