© 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. 93713
    Prev
    Next
    INDEX
    Explanations

    interpersonal relationships and character dynamics in narratives

    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
     Miami
    -0.10
    Miami
    -0.10
     Chanel
    -0.08
     Portsmouth
    -0.08
     Bahrain
    -0.08
     Southampton
    -0.08
     Mumbai
    -0.07
     Liverpool
    -0.07
     Venezuel
    -0.07
     Essex
    -0.07
    POSITIVE LOGITS
     Worcester
    0.09
    Kansas
    0.09
     Kansas
    0.08
    .azure
    0.08
     Sacramento
    0.08
     Hungarian
    0.08
    κ
    0.07
     Hungary
    0.07
     Maryland
    0.07
     Slovakia
    0.07
    Activations Density 0.199%

    No Known Activations