© 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. 118128
    Prev
    Next
    INDEX
    Explanations

    punctuation or sentence-ending markers

    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
    ARAM
    -0.07
    дина
    -0.07
    ifu
    -0.07
    ousel
    -0.07
    loth
    -0.06
    iffs
    -0.06
    aths
    -0.06
    ARGV
    -0.06
    AREST
    -0.06
     Bands
    -0.06
    POSITIVE LOGITS
    irit
    0.06
    eck
    0.06
    @dynamic
    0.06
    sv
    0.06
    iah
    0.06
    aber
    0.06
     Annunci
    0.06
    +xml
    0.06
    orsch
    0.05
    iot
    0.05
    Activations Density 0.000%

    No Known Activations