© 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. 117638
    Prev
    Next
    INDEX
    Explanations

    programming-related or technical terms

    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
    MOTE
    -0.07
    ikan
    -0.07
    unter
    -0.07
    851
    -0.06
    urette
    -0.06
    653
    -0.06
    olic
    -0.06
    meli
    -0.06
    unate
    -0.06
    fak
    -0.06
    POSITIVE LOGITS
    sville
    0.09
     Sunder
    0.07
     prol
    0.07
    .rev
    0.07
     tane
    0.06
    -exc
    0.06
    çĵľ
    0.06
    lendi
    0.06
    ãģĵãģ¡ãĤī
    0.06
    Inside
    0.06
    Activations Density 0.000%

    No Known Activations