Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87477
    Prev
    Next
    INDEX
    Explanations

    references to relationships and personal connections

    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
    á»Ĺng
    -0.08
    elmet
    -0.08
    steder
    -0.08
    astreet
    -0.08
    doch
    -0.08
    idak
    -0.07
    Exited
    -0.07
    .useState
    -0.07
    ÙĨدÙĬ
    -0.07
    -âĢIJ
    -0.07
    POSITIVE LOGITS
     fellow
    0.15
     friend
    0.13
     colleague
    0.11
     Friend
    0.10
     neighbour
    0.10
     rival
    0.10
     competitor
    0.10
     Fellow
    0.09
     sibling
    0.09
     neighbor
    0.09
    Activations Density 0.022%

    No Known Activations