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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 55757
    Prev
    Next
    INDEX
    Explanations

    phrases related to food preparation and preservation

    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
    oksen
    -0.06
    ilk
    -0.06
    ÐĴÐŀ
    -0.06
     VÅ¡ech
    -0.06
    ublic
    -0.06
    .Preference
    -0.06
    uç
    -0.06
    orra
    -0.06
    еÑħ
    -0.06
    éné
    -0.06
    POSITIVE LOGITS
     whenever
    0.09
    keh
    0.08
     Whenever
    0.08
    .ready
    0.07
    Whenever
    0.07
    USES
    0.07
     ready
    0.06
    ¦
    0.06
    maid
    0.06
    ello
    0.06
    Activations Density 0.014%

    No Known Activations