© 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. 15-LLAMASCOPE-RES-131K
    11. 88920
    Prev
    Next
    INDEX
    Explanations

    concepts related to set theory and mathematical properties

    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
     both
    -0.07
    both
    -0.07
    rame
    -0.06
     all
    -0.06
    γή
    -0.06
     вÑģем
    -0.06
     Both
    -0.06
     the
    -0.06
    usted
    -0.06
    uden
    -0.06
    POSITIVE LOGITS
    æŁIJ
    0.14
     somebody
    0.12
     someone
    0.11
    someone
    0.11
     Somebody
    0.10
     Someone
    0.10
    Someone
    0.09
     certain
    0.09
     something
    0.08
     alguien
    0.08
    Activations Density 0.052%

    No Known Activations