© 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. 93632
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups of people

    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
    tk
    -0.08
    ster
    -0.07
    yor
    -0.07
    ت
    -0.07
    vert
    -0.07
    .Ui
    -0.07
    iness
    -0.07
    ging
    -0.07
    bach
    -0.07
    ford
    -0.06
    POSITIVE LOGITS
    nal
    0.08
    nel
    0.08
    als
    0.07
    ality
    0.07
    ally
    0.07
    weets
    0.07
    chestra
    0.07
    ités
    0.06
    piration
    0.06
    нок
    0.06
    Activations Density 0.007%

    No Known Activations