© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87330
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooking and ingredient availability

    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
    attery
    -0.07
    rens
    -0.07
    DOMNode
    -0.07
    ooter
    -0.06
    zel
    -0.06
    quil
    -0.06
    dorf
    -0.06
    enson
    -0.06
    ICAST
    -0.06
     anth
    -0.06
    POSITIVE LOGITS
     readily
    0.09
     household
    0.08
     households
    0.07
    isin
    0.07
     ingredients
    0.07
     pantry
    0.07
    \common
    0.07
    arded
    0.06
    aine
    0.06
     Household
    0.06
    Activations Density 0.014%

    No Known Activations