© 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 EvalsExportsinterp-engineNEWAPI 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. 92766
    Prev
    Next
    INDEX
    Explanations

    significant punctuation and specific high-frequency words in the text

    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
    stu
    -0.07
    ÑģÑĤÑĮ
    -0.07
    âĶĶ
    -0.07
    лаÑĩ
    -0.07
     triangle
    -0.07
     Triangle
    -0.07
    õi
    -0.07
    ÑĴ
    -0.06
    AbsolutePath
    -0.06
    jur
    -0.06
    POSITIVE LOGITS
    iban
    0.07
     coal
    0.06
     reserve
    0.06
    ï¸
    0.06
     vit
    0.06
    Mine
    0.05
    ç´
    0.05
    atee
    0.05
    itere
    0.05
    ueue
    0.05
    Activations Density 0.000%

    No Known Activations