© 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. 83330
    Prev
    Next
    INDEX
    Explanations

    inquiries about searching and exploring various places or meanings

    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
    ifu
    -0.07
    arest
    -0.07
    ouz
    -0.07
    ancell
    -0.07
    engo
    -0.06
    kem
    -0.06
    uzzi
    -0.06
    oca
    -0.06
     Facilities
    -0.06
    onces
    -0.06
    POSITIVE LOGITS
     search
    0.12
    search
    0.11
     Search
    0.11
    -search
    0.10
    Search
    0.10
    _search
    0.10
     SEARCH
    0.10
    SEARCH
    0.10
     searching
    0.09
    .search
    0.09
    Activations Density 0.074%

    No Known Activations