© 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. 116866
    Prev
    Next
    INDEX
    Explanations

    mentions of avocados and related culinary 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
    hardt
    -0.07
    asca
    -0.07
     Gry
    -0.07
    bulk
    -0.07
    ç¨
    -0.06
     bulk
    -0.06
    SPA
    -0.06
     Dtype
    -0.06
    _aut
    -0.06
     grains
    -0.06
    POSITIVE LOGITS
     avocado
    0.08
    kins
    0.07
     oil
    0.07
    -tree
    0.07
     rall
    0.07
    kin
    0.07
    ł
    0.07
    mî
    0.07
    leich
    0.07
     Teh
    0.06
    Activations Density 0.011%

    No Known Activations