© 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. 54796
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer interactions and product management

    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
    stad
    -0.07
    rang
    -0.07
    irsch
    -0.07
     Welch
    -0.06
    oru
    -0.06
    Loop
    -0.06
    isel
    -0.06
    urovision
    -0.06
    оÑĤов
    -0.06
    gmt
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.13
     somewhere
    0.11
     chez
    0.10
     venue
    0.09
     visit
    0.09
    æĶ¾åľ¨
    0.09
    çļĦåľ°æĸ¹
    0.08
     places
    0.08
    Venue
    0.08
     Venue
    0.08
    Activations Density 0.106%

    No Known Activations