© 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. 15-LLAMASCOPE-RES-131K
    11. 87447
    Prev
    Next
    INDEX
    Explanations

    instances of dependent clauses or phrases within sentences

    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
    iqu
    -0.08
    mere
    -0.07
    ithe
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
    bart
    -0.07
    егоÑĢ
    -0.07
    zell
    -0.07
    eneral
    -0.07
    lain
    -0.06
    alysis
    -0.06
    POSITIVE LOGITS
     because
    0.07
     Independ
    0.07
    Stripe
    0.06
    æĹ¢çĦ¶
    0.06
     wenn
    0.06
    ftype
    0.06
    iven
    0.06
    phans
    0.06
     dress
    0.06
     lint
    0.06
    Activations Density 0.011%

    No Known Activations