© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75239
    Prev
    Next
    INDEX
    Explanations

    titles and positions related to leadership and management roles

    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
     assistant
    -0.08
    assistant
    -0.07
     Assistant
    -0.07
     assistants
    -0.07
    jun
    -0.07
    Assistant
    -0.07
    796
    -0.06
    \Helper
    -0.06
     department
    -0.06
    Junior
    -0.06
    POSITIVE LOGITS
     founder
    0.17
     Founder
    0.15
    Founder
    0.14
     founders
    0.12
     CEO
    0.11
    -founder
    0.11
     founding
    0.11
     owner
    0.10
     founded
    0.10
     proprietor
    0.10
    Activations Density 0.030%

    No Known Activations