© 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 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. 77244
    Prev
    Next
    INDEX
    Explanations

    terms related to business metrics and evaluations

    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
    med
    -0.06
     dop
    -0.06
     Saul
    -0.06
     Nixon
    -0.06
    iva
    -0.05
     Dong
    -0.05
     Show
    -0.05
     status
    -0.05
    ried
    -0.05
    ừ
    -0.05
    POSITIVE LOGITS
    avaÅŁ
    0.08
    hlen
    0.08
    ombat
    0.08
     Äijiá»ĥn
    0.08
     thôi
    0.08
     suce
    0.07
     Ratings
    0.07
    ipsis
    0.07
    ãĥ¼ãĥĹ
    0.07
    _ratings
    0.07
    Activations Density 0.000%

    No Known Activations