© 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. 78318
    Prev
    Next
    INDEX
    Explanations

    key concepts related to product quality and customer service

    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
    324
    -0.06
     vitam
    -0.06
    voy
    -0.06
     XmlDocument
    -0.06
    maal
    -0.06
    ale
    -0.06
    iken
    -0.05
    opyright
    -0.05
    ultz
    -0.05
     Jonathan
    -0.05
    POSITIVE LOGITS
    kad
    0.08
    PRICE
    0.07
     hemisphere
    0.07
    ackets
    0.07
    adro
    0.06
     Downs
    0.06
    adol
    0.06
     price
    0.06
    itten
    0.06
    ahi
    0.06
    Activations Density 0.000%

    No Known Activations