© 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. 131045
    Prev
    Next
    INDEX
    Explanations

    phrases related to loss and missing elements

    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
    ipa
    -0.07
    ÑĢÑĸÑĪ
    -0.06
    ľ´
    -0.06
    372
    -0.06
    init
    -0.06
    ngr
    -0.06
     dormant
    -0.06
    odka
    -0.06
    ADS
    -0.06
     /^(
    -0.06
    POSITIVE LOGITS
     anymore
    0.22
     now
    0.12
     continued
    0.12
     nữa
    0.12
    continued
    0.12
     continuing
    0.11
     remaining
    0.11
     continues
    0.11
     continue
    0.10
     Continued
    0.10
    Activations Density 0.111%

    No Known Activations