© 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. 119682
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities related to counting and measurements

    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
    寺
    -0.06
     Ars
    -0.06
     percentages
    -0.06
    /cms
    -0.06
     Rowe
    -0.06
    lists
    -0.06
    iec
    -0.06
    ýš
    -0.06
    (LP
    -0.06
    #echo
    -0.06
    POSITIVE LOGITS
    imax
    0.08
    ména
    0.07
    tober
    0.07
    oplevel
    0.07
    abbo
    0.06
    aber
    0.06
     consect
    0.06
     times
    0.06
    usterity
    0.06
    تÙĪ
    0.06
    Activations Density 0.040%

    No Known Activations