© 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. 82463
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes in the text

    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
    erd
    -0.06
    agna
    -0.06
    eczy
    -0.06
     Weather
    -0.06
    zet
    -0.06
    oot
    -0.06
    ãĤ¤ãĥĦ
    -0.06
    ìĿ´íģ¬
    -0.06
    aming
    -0.06
    ething
    -0.06
    POSITIVE LOGITS
    EIF
    0.07
     Giles
    0.07
    éľ
    0.07
    .neo
    0.07
    imest
    0.07
    èĵ
    0.07
    ãĤ¤ãĥĪ
    0.07
    linkplain
    0.07
    /calendar
    0.07
    tica
    0.06
    Activations Density 0.004%

    No Known Activations