© 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. 76211
    Prev
    Next
    INDEX
    Explanations

    food and related culinary terminology

    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
    .LookAndFeel
    -0.07
    oen
    -0.07
    ãĥ¼ãĥķ
    -0.07
    adena
    -0.07
    esini
    -0.07
     rowspan
    -0.07
    pga
    -0.06
    cast
    -0.06
    Spo
    -0.06
    iÄħ
    -0.06
    POSITIVE LOGITS
    -style
    0.08
    edes
    0.07
    ë§ģ
    0.07
    oter
    0.06
     einf
    0.06
     served
    0.06
    eros
    0.06
    ero
    0.06
     Traditional
    0.06
    -shell
    0.06
    Activations Density 0.043%

    No Known Activations