© 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. 95413
    Prev
    Next
    INDEX
    Explanations

    locations and distances related to hotels and attractions

    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
    flip
    -0.07
     Kane
    -0.07
    rowse
    -0.07
    gard
    -0.06
    880
    -0.06
    òng
    -0.06
    dbg
    -0.06
    ett
    -0.06
    spell
    -0.06
     flip
    -0.06
    POSITIVE LOGITS
    aal
    0.07
    okedex
    0.06
     advantage
    0.06
    ัà¸Ļà¸Ļ
    0.06
     sav
    0.06
     convenience
    0.06
     Convenience
    0.06
    ","");↵
    0.06
     conc
    0.06
    InParameter
    0.06
    Activations Density 0.002%

    No Known Activations