© 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. 118169
    Prev
    Next
    INDEX
    Explanations

    references to user interface components in programming 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
    微软éĽħé»ij
    -0.07
    гÑĢад
    -0.07
    _sink
    -0.07
    sink
    -0.06
    asz
    -0.06
    iais
    -0.06
    ux
    -0.06
    aves
    -0.06
    utes
    -0.06
    acos
    -0.06
    POSITIVE LOGITS
    /wiki
    0.07
    imals
    0.07
    /datatables
    0.06
    679
    0.06
    .dm
    0.06
    OTA
    0.06
    USB
    0.06
    TEGER
    0.06
     Rah
    0.06
    845
    0.06
    Activations Density 0.001%

    No Known Activations