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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43541
    Prev
    Next
    INDEX
    Explanations

    information related to car safety ratings and features

    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
    .CustomButton
    -0.06
    oria
    -0.06
    AMPL
    -0.06
    atron
    -0.06
     disfr
    -0.06
    SPELL
    -0.06
    Ship
    -0.06
    ÏĦεÏģ
    -0.06
     ~/.
    -0.06
    ORIZ
    -0.06
    POSITIVE LOGITS
     crash
    0.14
     NC
    0.12
     Crash
    0.12
     Euro
    0.12
     ratings
    0.12
     rating
    0.11
     safety
    0.11
     tests
    0.11
     frontal
    0.10
     testing
    0.10
    Activations Density 0.010%

    No Known Activations