© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126778
    Prev
    Next
    INDEX
    Explanations

    specific words or identifiers related to programming or configuration details

    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
    ense
    -0.07
    issan
    -0.06
    irt
    -0.06
    663
    -0.06
    496
    -0.06
    WER
    -0.06
     trial
    -0.06
     tick
    -0.06
    208
    -0.05
     myth
    -0.05
    POSITIVE LOGITS
    ÙĤÙĪÙĦ
    0.07
    .scalablytyped
    0.07
    pta
    0.07
    sad
    0.07
     WHATSOEVER
    0.07
    oled
    0.07
    sut
    0.06
    è¡
    0.06
    ¾
    0.06
    uÃŃ
    0.06
    Activations Density 0.073%

    No Known Activations