© 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. 61543
    Prev
    Next
    INDEX
    Explanations

    keywords related to HTML and CSS coding

    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
    Tier
    -0.07
    ezi
    -0.07
    atatype
    -0.07
    atische
    -0.07
    OMPI
    -0.07
    ignum
    -0.07
    ekten
    -0.07
    culus
    -0.07
    apolis
    -0.07
    ftware
    -0.07
    POSITIVE LOGITS
     resid
    0.07
    icc
    0.07
     Document
    0.07
    Document
    0.06
     document
    0.06
    cano
    0.06
     Eric
    0.06
     Vacc
    0.06
    NSS
    0.06
     fungal
    0.06
    Activations Density 0.019%

    No Known Activations