© 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. 3397
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events, particularly those involving attacks and their impacts

    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
    ecycle
    -0.06
    isce
    -0.06
    éį
    -0.06
    ertos
    -0.06
    ngo
    -0.06
    èįĴ
    -0.06
     pressures
    -0.06
    alaria
    -0.06
    quette
    -0.06
    .press
    -0.06
    POSITIVE LOGITS
    apping
    0.06
     mass
    0.06
     towers
    0.06
     Willi
    0.06
     Americans
    0.06
    owers
    0.06
    mass
    0.06
     unthinkable
    0.06
     leisure
    0.06
     hij
    0.06
    Activations Density 0.027%

    No Known Activations