Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118725
    Prev
    Next
    INDEX
    Explanations

    sentiments related to media portrayal and public perception

    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
    ekk
    -0.06
     Price
    -0.06
     base
    -0.05
     trusted
    -0.05
     total
    -0.05
    onom
    -0.05
    ennen
    -0.05
    â̦↵
    -0.05
     extension
    -0.05
     Prices
    -0.05
    POSITIVE LOGITS
    Lazy
    0.09
    acente
    0.08
    lazy
    0.08
     Lazy
    0.08
    sexy
    0.08
     sexy
    0.08
    zia
    0.07
     fisse
    0.07
     splash
    0.07
     ../../../
    0.07
    Activations Density 0.031%

    No Known Activations