© 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. 15-LLAMASCOPE-RES-131K
    11. 61817
    Prev
    Next
    INDEX
    Explanations

    ingredients and substances related to food and cooking

    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
    inn
    -0.06
     Kaf
    -0.06
     Sm
    -0.06
     Boo
    -0.06
     the
    -0.06
     Turtle
    -0.06
     jams
    -0.05
    ÙĪØ«
    -0.05
    ter
    -0.05
    -of
    -0.05
    POSITIVE LOGITS
    ovah
    0.08
    ahlen
    0.08
    acier
    0.07
    κÏģα
    0.07
    plode
    0.07
    gnore
    0.07
    hower
    0.07
    è´¨
    0.07
    Ware
    0.07
    oose
    0.07
    Activations Density 0.024%

    No Known Activations