© 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. 125551
    Prev
    Next
    INDEX
    Explanations

    actions related to the introduction or implementation of policies and programs

    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
    /Runtime
    -0.08
    essler
    -0.08
    iyah
    -0.08
    imuth
    -0.07
    kup
    -0.07
     ÙħÛĮÙĦادÛĮ
    -0.07
    geber
    -0.07
    itur
    -0.07
    igraph
    -0.07
    chemy
    -0.07
    POSITIVE LOGITS
     by
    0.07
     since
    0.07
     now
    0.07
     earlier
    0.07
     perhaps
    0.06
     previously
    0.06
     .
    0.06
     always
    0.06
    0.05
     them
    0.05
    Activations Density 0.053%

    No Known Activations