© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78798
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terminologies related to graph theory

    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
     Pant
    -0.07
    bette
    -0.07
    aml
    -0.07
    ehler
    -0.07
    illac
    -0.07
    æĬĺ
    -0.07
    emi
    -0.07
    oil
    -0.06
    aat
    -0.06
    agal
    -0.06
    POSITIVE LOGITS
     Majority
    0.06
    indy
    0.06
     social
    0.06
     prov
    0.06
    party
    0.06
     random
    0.06
     parties
    0.06
    617
    0.06
     Erd
    0.06
     vertex
    0.06
    Activations Density 0.077%

    No Known Activations