© 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. 126011
    Prev
    Next
    INDEX
    Explanations

    references to personal hardship and career transitions

    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
    iration
    -0.07
     nodeId
    -0.07
    .nano
    -0.07
    antium
    -0.07
    lobal
    -0.07
    abin
    -0.06
    lds
    -0.06
    overy
    -0.06
    chine
    -0.06
     åĥ
    -0.06
    POSITIVE LOGITS
     business
    0.10
     profit
    0.08
    business
    0.07
     businesses
    0.07
     profits
    0.07
     Cong
    0.07
     Business
    0.07
    غÙĦ
    0.06
     purchase
    0.06
     investments
    0.06
    Activations Density 0.019%

    No Known Activations