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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5255
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership, sustainability, and consumer engagement

    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
    rix
    -0.06
    antasy
    -0.06
    ius
    -0.06
    oÅĪ
    -0.06
    borough
    -0.06
    Duplicates
    -0.06
     getSystemService
    -0.06
    äºŃ
    -0.06
    .inflate
    -0.06
    Security
    -0.06
    POSITIVE LOGITS
     authenticity
    0.12
     Authentic
    0.11
     authentic
    0.10
     brands
    0.09
     consumers
    0.09
    Auth
    0.09
     auth
    0.09
     brand
    0.09
    auth
    0.09
     Brands
    0.08
    Activations Density 0.008%

    No Known Activations