© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119313
    Prev
    Next
    INDEX
    Explanations

    occurrences of quotations and reported speech

    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
    ancock
    -0.08
    psilon
    -0.08
    ----</
    -0.08
    -------------</
    -0.07
    LÄ°
    -0.07
    öyle
    -0.07
    áºŃc
    -0.07
    Ðĭ
    -0.07
    Compatible
    -0.07
     zdrav
    -0.07
    POSITIVE LOGITS
     another
    0.09
     again
    0.07
    æĥħ
    0.06
     pul
    0.06
    åıĪ
    0.06
    another
    0.06
    ãģ¾ãģŁ
    0.06
     yine
    0.06
    Another
    0.06
    ULD
    0.06
    Activations Density 0.013%

    No Known Activations