© 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. 87624
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to significant contributions or roles played by individuals

    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
    .getOwnProperty
    -0.08
    jedn
    -0.08
    esso
    -0.08
    andise
    -0.07
    PRINTF
    -0.07
    adden
    -0.07
    arus
    -0.07
    riott
    -0.07
    رÛĮÙħ
    -0.07
    xes
    -0.07
    POSITIVE LOGITS
     pushing
    0.07
     behind
    0.07
     hub
    0.07
     design
    0.06
     during
    0.06
     dur
    0.06
     instrumental
    0.06
     help
    0.06
     Hub
    0.06
     bringing
    0.06
    Activations Density 0.018%

    No Known Activations