© 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. 78174
    Prev
    Next
    INDEX
    Explanations

    terms related to dairy products and their consumption

    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
    ning
    -0.08
    Ñĩини
    -0.07
    ners
    -0.06
    irsch
    -0.06
    gra
    -0.06
    .UnitTesting
    -0.06
    ght
    -0.06
    balances
    -0.06
     licensors
    -0.06
     kino
    -0.06
    POSITIVE LOGITS
     milk
    0.09
     Milk
    0.07
     Smy
    0.07
    èĪį
    0.07
    iously
    0.06
     tiết
    0.06
    /me
    0.06
     süt
    0.06
    efully
    0.06
    emons
    0.06
    Activations Density 0.005%

    No Known Activations