© 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. 87178
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cover" and its variants, particularly in contexts related to healthcare and protection

    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
    §è¡Į
    -0.09
    hma
    -0.07
    ès
    -0.07
    .opendaylight
    -0.07
    inge
    -0.07
    rets
    -0.07
    CKET
    -0.06
    mrt
    -0.06
    elib
    -0.06
    .listFiles
    -0.06
    POSITIVE LOGITS
    454
    0.07
    723
    0.07
    .cover
    0.06
     rapid
    0.06
    leur
    0.06
    yl
    0.06
     laps
    0.06
     fal
    0.06
     Coverage
    0.06
    -cover
    0.06
    Activations Density 0.009%

    No Known Activations