© 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. 105270
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "and" along with various punctuation, suggesting a focus on conjunctions and lists

    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
    ripe
    -0.07
    ksam
    -0.06
    беÑĢ
    -0.06
    iffe
    -0.06
    hoff
    -0.06
    rip
    -0.06
    nou
    -0.06
    æīĭãĤĴ
    -0.06
    mond
    -0.06
     åı·
    -0.06
    POSITIVE LOGITS
    eslint
    0.07
    antro
    0.06
     Dillon
    0.06
    رÙĪع
    0.06
    _share
    0.06
    arkin
    0.06
    poi
    0.06
    plib
    0.06
     followed
    0.06
    _exports
    0.06
    Activations Density 0.004%

    No Known Activations