© 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. 79274
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to searching or identifying specific information or entities

    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
    ll
    -0.07
    eka
    -0.07
    linger
    -0.07
     mound
    -0.07
     pie
    -0.06
    esters
    -0.06
     fiance
    -0.06
    ÙģÙĩ
    -0.06
    izon
    -0.06
    urb
    -0.06
    POSITIVE LOGITS
    ona
    0.07
     whether
    0.07
     optimal
    0.07
    .ix
    0.06
    jis
    0.06
    ONA
    0.06
     Sterling
    0.06
    opt
    0.06
     Opt
    0.06
     prime
    0.06
    Activations Density 0.052%

    No Known Activations