© 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. 76812
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software configurations and policies

    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
    467
    -0.06
    iphy
    -0.06
    ané
    -0.06
    berman
    -0.06
    aison
    -0.06
    prech
    -0.06
    apiro
    -0.06
    gether
    -0.06
    ettings
    -0.06
    .debian
    -0.06
    POSITIVE LOGITS
     null
    0.08
     nil
    0.08
     nothing
    0.07
     NULL
    0.07
     nulla
    0.06
    )NULL
    0.06
     None
    0.06
     nullptr
    0.06
    (null
    0.06
    apel
    0.06
    Activations Density 0.011%

    No Known Activations