© 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. 77583
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between different subjects or groups

    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
    illion
    -0.07
    _UTF
    -0.07
    antino
    -0.07
    ument
    -0.07
    ouz
    -0.07
    isiyle
    -0.06
    illon
    -0.06
    deniz
    -0.06
    avor
    -0.06
    757
    -0.06
    POSITIVE LOGITS
     consumer
    0.09
     actual
    0.08
     individual
    0.08
     consumers
    0.08
    Consumer
    0.08
    consumer
    0.08
     Consumer
    0.07
    arov
    0.07
     patients
    0.06
     patient
    0.06
    Activations Density 0.029%

    No Known Activations