© 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. 57178
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to health, nutrition, and dietary advice

    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
    ожд
    -0.07
    rippling
    -0.07
    .bio
    -0.07
    bjerg
    -0.07
     åł
    -0.06
     Lun
    -0.06
    angl
    -0.06
    elight
    -0.06
    nett
    -0.06
    ilio
    -0.06
    POSITIVE LOGITS
     Weight
    0.07
    ube
    0.07
    unky
    0.07
     Obesity
    0.07
     weight
    0.07
     overweight
    0.07
     poids
    0.06
     obesity
    0.06
    .weight
    0.06
    _recall
    0.06
    Activations Density 0.009%

    No Known Activations