© 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. 127516
    Prev
    Next
    INDEX
    Explanations

    references to actions and instructions related to improvement and personal accountability

    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
    oref
    -0.08
    amas
    -0.08
    olean
    -0.07
    irit
    -0.07
    eway
    -0.07
    iyim
    -0.07
    etCode
    -0.07
    OpenHelper
    -0.07
    kok
    -0.07
    ascal
    -0.07
    POSITIVE LOGITS
     again
    0.19
    again
    0.15
     novamente
    0.14
    Again
    0.14
     Again
    0.14
    åĨį
    0.12
     wieder
    0.11
     Ñģнова
    0.11
    åıĪ
    0.10
     znovu
    0.10
    Activations Density 0.019%

    No Known Activations