© 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. 17-LLAMASCOPE-RES-131K
    11. 57978
    Prev
    Next
    INDEX
    Explanations

    terms related to digital identifiers and their use in improving management systems

    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
    aign
    -0.07
     ide
    -0.06
     Eis
    -0.06
    571
    -0.06
    iaux
    -0.06
     infl
    -0.06
    ãģĭãģª
    -0.06
    å¼ĺ
    -0.06
    åº
    -0.06
     agricult
    -0.06
    POSITIVE LOGITS
    Æ¡
    0.07
    interopRequire
    0.07
    icipants
    0.07
    bern
    0.07
    imli
    0.07
    ousel
    0.07
    imple
    0.07
    jedn
    0.07
    ikip
    0.07
    orners
    0.07
    Activations Density 0.001%

    No Known Activations