© 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. 130140
    Prev
    Next
    INDEX
    Explanations

    concepts related to entropy and material defects

    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
    hea
    -0.09
    eyen
    -0.08
    alse
    -0.07
    monkey
    -0.07
    èįī
    -0.07
    abay
    -0.07
    onse
    -0.07
    ÅĻet
    -0.07
    eno
    -0.07
    alcon
    -0.06
    POSITIVE LOGITS
     vacant
    0.07
     Migration
    0.07
     vacancies
    0.07
     sites
    0.06
     addition
    0.06
     migration
    0.06
     additions
    0.06
     foreign
    0.06
     introduced
    0.06
     thêm
    0.06
    Activations Density 0.014%

    No Known Activations