© 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. 15-LLAMASCOPE-RES-131K
    11. 27526
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant elements or features within a text

    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
     (
    -0.06
     dot
    -0.06
     promised
    -0.06
     already
    -0.06
     promise
    -0.06
    ite
    -0.06
    abus
    -0.05
    emoc
    -0.05
     sh
    -0.05
     transactions
    -0.05
    POSITIVE LOGITS
    quential
    0.08
    ovah
    0.08
    ÙĪÛĮÙĨ
    0.08
    ãĤ¤ãĥĦ
    0.08
    HEST
    0.08
     кÑĥлÑĮ
    0.08
    ovÃŃ
    0.08
    mamak
    0.07
    macros
    0.07
     æ°
    0.07
    Activations Density 0.000%

    No Known Activations