© 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. 3791
    Prev
    Next
    INDEX
    Explanations

    fragments of programming syntax related to shared properties and configurations

    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
    iste
    -0.07
    вÑĸÑĤ
    -0.06
     Pager
    -0.05
    kil
    -0.05
    pps
    -0.05
     looping
    -0.05
    arih
    -0.05
    宾
    -0.05
    ooo
    -0.05
    itch
    -0.05
    POSITIVE LOGITS
    imir
    0.08
    óng
    0.07
    IGNAL
    0.06
    Campaign
    0.06
    jedn
    0.06
    avaÅŁ
    0.06
    xbd
    0.06
    etti
    0.06
    OUNCE
    0.06
    vanished
    0.06
    Activations Density 0.046%

    No Known Activations