© 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. 90259
    Prev
    Next
    INDEX
    Explanations

    culinary or food-related terms and references

    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
     ips
    -0.06
    коÑĤ
    -0.06
    cry
    -0.06
    iland
    -0.06
    trys
    -0.06
    layer
    -0.06
    .ping
    -0.06
     Fallen
    -0.06
     Valk
    -0.06
    eyn
    -0.06
    POSITIVE LOGITS
    erson
    0.07
    ptune
    0.06
     Plantae
    0.06
    onium
    0.06
     kum
    0.06
    ounder
    0.06
     Bhar
    0.06
    IEW
    0.06
     subplot
    0.06
     draining
    0.06
    Activations Density 0.058%

    No Known Activations