© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3934
    Prev
    Next
    INDEX
    Explanations

    words related to cooking and food ingredients

    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
    laden
    -0.07
    tes
    -0.07
    enthal
    -0.06
    oit
    -0.06
     Latter
    -0.06
    eous
    -0.06
    ETS
    -0.06
    prises
    -0.06
    til
    -0.06
    865
    -0.06
    POSITIVE LOGITS
    imony
    0.12
    imon
    0.08
    ley
    0.08
    opak
    0.08
    vak
    0.07
    agon
    0.07
    nger
    0.07
    LEY
    0.07
    nip
    0.07
    ĶĶ
    0.07
    Activations Density 0.002%

    No Known Activations