© 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. 57593
    Prev
    Next
    INDEX
    Explanations

    names of individuals associated with inventions or references in patent applications

    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
    ówn
    -0.06
    /feed
    -0.06
    csi
    -0.06
    amet
    -0.06
    ãģ¹ãģ¦
    -0.06
    iap
    -0.06
    RowAt
    -0.06
    kili
    -0.06
     baiser
    -0.06
    cert
    -0.06
    POSITIVE LOGITS
    odore
    0.09
     A
    0.08
    imuth
    0.07
    ॰
    0.07
     E
    0.07
     J
    0.07
     Mrs
    0.07
    ÑģÑĤÑĢе
    0.06
    obuf
    0.06
     &,
    0.06
    Activations Density 0.078%

    No Known Activations