© 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. 118351
    Prev
    Next
    INDEX
    Explanations

    phrases that compare or describe items as a type or category

    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
    itm
    -0.07
    ANTS
    -0.06
    ough
    -0.06
    spb
    -0.06
    lock
    -0.06
    celik
    -0.06
    onne
    -0.06
    Ton
    -0.06
    555
    -0.06
     aç
    -0.06
    POSITIVE LOGITS
    eldo
    0.08
    arcy
    0.07
    Ø°
    0.07
    ehir
    0.07
     stripslashes
    0.07
     souÄįást
    0.07
     aid
    0.06
    ctal
    0.06
    jev
    0.06
    ÄĽti
    0.06
    Activations Density 0.024%

    No Known Activations