© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 99265
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity of expertise or qualifications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    insky
    -0.07
    ibri
    -0.06
    tesy
    -0.06
    ÅĻev
    -0.06
    ĥ
    -0.06
    witter
    -0.06
    _RANK
    -0.06
    strtolower
    -0.06
    ilim
    -0.06
    emark
    -0.06
    POSITIVE LOGITS
     Barth
    0.07
    æŁĵ
    0.06
    797
    0.06
     Mason
    0.06
     Danger
    0.06
    tings
    0.06
    assi
    0.06
     ÐŀÑģÑĤ
    0.06
     barn
    0.06
    ãĤ¿ãĥ«
    0.06
    Activations Density 0.007%

    No Known Activations