© 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. 29092
    Prev
    Next
    INDEX
    Explanations

    phrases related to network connection errors and exceptions

    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
    flix
    -0.08
    uien
    -0.07
    ffen
    -0.07
    iscard
    -0.07
    ritel
    -0.07
    onces
    -0.06
    rouch
    -0.06
    Ðĩ
    -0.06
    unks
    -0.06
    eday
    -0.06
    POSITIVE LOGITS
    Translator
    0.06
    rogen
    0.06
     stat
    0.06
     Duel
    0.06
    uppe
    0.06
    Stat
    0.06
    GS
    0.05
    Ñĥже
    0.05
    .Link
    0.05
    AGAIN
    0.05
    Activations Density 0.005%

    No Known Activations