© 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. 117619
    Prev
    Next
    INDEX
    Explanations

    references to beer and wine

    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
    ors
    -0.08
    en
    -0.07
    ting
    -0.07
    mente
    -0.07
    ure
    -0.07
    ents
    -0.07
    tt
    -0.07
    aire
    -0.07
    al
    -0.07
    yon
    -0.07
    POSITIVE LOGITS
    кеÑĤ
    0.09
    ส
    0.08
    zeug
    0.08
    žÃŃ
    0.08
    eries
    0.08
    bower
    0.07
    تÙĦ
    0.07
    ormsg
    0.07
    igung
    0.07
    keeping
    0.07
    Activations Density 0.005%

    No Known Activations