© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1294
    Prev
    Next
    INDEX
    Explanations

    phrases related to dining experiences and restaurant offerings

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ź
    -0.06
    ovic
    -0.06
    itur
    -0.06
    ãĥ³ãĤ°ãĥ«
    -0.06
    اÙĬÙĨ
    -0.06
    roph
    -0.06
    Ìģt
    -0.06
    éné
    -0.06
    /resource
    -0.06
     Dess
    -0.06
    POSITIVE LOGITS
     our
    0.08
    atat
    0.07
     Claw
    0.07
     nostro
    0.07
    fare
    0.07
    egra
    0.07
    atism
    0.06
    atron
    0.06
     specials
    0.06
     nostra
    0.06
    Activations Density 0.015%

    No Known Activations