© 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. 40107
    Prev
    Next
    INDEX
    Explanations

    phrases related to insurance and its importance

    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
     discretion
    -0.09
    bitrary
    -0.06
    vier
    -0.06
    arto
    -0.06
    nett
    -0.06
    itr
    -0.06
    ARING
    -0.06
    etroit
    -0.05
    ETF
    -0.05
    éº
    -0.05
    POSITIVE LOGITS
     insurance
    0.16
     coverage
    0.15
    coverage
    0.14
     Insurance
    0.13
    Coverage
    0.13
     Coverage
    0.13
    insurance
    0.12
    Insurance
    0.12
     protection
    0.11
    _coverage
    0.10
    Activations Density 0.045%

    No Known Activations