© 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 EvalsExportsinterp-engineNEWAPI 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. 72880
    Prev
    Next
    INDEX
    Explanations

    instances of the word "blog" and related terms in various contexts

    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
    UNS
    -0.07
    using
    -0.07
    Trivia
    -0.07
    unks
    -0.07
     Telegram
    -0.07
     ÛĮÙĪتÛĮ
    -0.07
    ÙĨاÙħÙĩ
    -0.07
    ingo
    -0.07
    .stamp
    -0.07
    porter
    -0.07
    POSITIVE LOGITS
     sham
    0.06
     Jab
    0.06
     ask
    0.05
     Roland
    0.05
    ArrayOf
    0.05
    otton
    0.05
    asc
    0.05
    _alias
    0.05
    inish
    0.05
     Isl
    0.05
    Activations Density 0.004%

    No Known Activations