Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84279
    Prev
    Next
    INDEX
    Explanations

    expressions of pleasure or enjoyment related to food

    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
    ed
    -0.09
    cheng
    -0.07
    edb
    -0.07
    ppard
    -0.06
    edBy
    -0.06
    ors
    -0.06
    ndon
    -0.06
    ented
    -0.06
    quo
    -0.05
    ưng
    -0.05
    POSITIVE LOGITS
    ButtonType
    0.07
    etti
    0.07
    iversit
    0.07
    yat
    0.07
    WriteBarrier
    0.07
    ãģĸ
    0.07
     Ders
    0.07
    dden
    0.07
    LOPT
    0.07
    ingly
    0.07
    Activations Density 0.003%

    No Known Activations