© 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. 5-LLAMASCOPE-RES-131K
    11. 125707
    Prev
    Next
    INDEX
    Explanations

    Addresses of locations mentioned in the document

    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
    erno
    -0.06
    quil
    -0.06
    sw
    -0.06
    elsea
    -0.06
    urn
    -0.06
    dden
    -0.06
    orts
    -0.06
    338
    -0.06
    GRAM
    -0.05
    imir
    -0.05
    POSITIVE LOGITS
    _SI
    0.07
     Dunk
    0.07
    éijij
    0.07
    ìŀIJìĿ¸
    0.07
    ensitive
    0.07
    oji
    0.06
    ladu
    0.06
    lug
    0.06
    bsolute
    0.06
    zych
    0.06
    Activations Density 0.004%

    No Known Activations