© 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. 95785
    Prev
    Next
    INDEX
    Explanations

    phrases expressing frustration over a lack of information or assistance

    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
    ieber
    -0.07
    insk
    -0.06
    enal
    -0.06
    inz
    -0.06
    ht
    -0.06
    ebra
    -0.06
    341
    -0.06
    etten
    -0.06
     trivia
    -0.06
    776
    -0.06
    POSITIVE LOGITS
     searches
    0.11
    æIJľç´¢
    0.11
     search
    0.10
     searched
    0.10
     searching
    0.10
    SEARCH
    0.10
    -search
    0.09
    search
    0.09
    .search
    0.09
    (search
    0.09
    Activations Density 0.009%

    No Known Activations