© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94585
    Prev
    Next
    INDEX
    Explanations

    information related to rental car insurance coverage

    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
    ána
    -0.07
    ana
    -0.07
    ANA
    -0.07
    earn
    -0.07
    cks
    -0.06
    una
    -0.06
    GIN
    -0.06
    _MISS
    -0.06
    emd
    -0.06
     scr
    -0.06
    POSITIVE LOGITS
    coverage
    0.11
     Coverage
    0.11
     coverage
    0.11
    _coverage
    0.09
    Coverage
    0.09
     Cover
    0.07
    andro
    0.07
     policy
    0.06
    policy
    0.06
    Policy
    0.06
    Activations Density 0.009%

    No Known Activations