© 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. 16159
    Prev
    Next
    INDEX
    Explanations

    concepts related to case management and public health initiatives

    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
    hetto
    -0.07
    ust
    -0.07
    kins
    -0.07
    uste
    -0.06
    opers
    -0.06
     Marcus
    -0.06
     Fro
    -0.06
    vara
    -0.06
    acus
    -0.06
    714
    -0.06
    POSITIVE LOGITS
     ran
    0.07
    .run
    0.07
     run
    0.07
     affairs
    0.07
     runs
    0.07
    æ¢Ŀ
    0.07
    .runners
    0.06
    è·ij
    0.06
    (run
    0.06
    .RunWith
    0.06
    Activations Density 0.051%

    No Known Activations