© 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. 4096
    Prev
    Next
    INDEX
    Explanations

    words indicating capability or ability

    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
    onds
    -0.07
    Ø´ÙħاÙĦÛĮ
    -0.07
    ected
    -0.07
    enty
    -0.06
    éric
    -0.06
    nds
    -0.06
    gregation
    -0.06
    .selenium
    -0.06
     nutzen
    -0.06
    odo
    -0.06
    POSITIVE LOGITS
    PRESS
    0.07
    PU
    0.07
    ilk
    0.06
    ilver
    0.06
    wick
    0.06
     weight
    0.06
    ipers
    0.06
    oloj
    0.06
     Essence
    0.06
    ħ
    0.06
    Activations Density 0.000%

    No Known Activations