© 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. 15-LLAMASCOPE-RES-131K
    11. 89922
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific measurements and astronomical phenomena

    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
     Horton
    -0.06
    ostel
    -0.06
    ichern
    -0.06
    ety
    -0.06
    igator
    -0.06
    ãĥĩãĤ£ãĥ¼ãĤ¹
    -0.06
     Backpack
    -0.06
    apyrus
    -0.06
    nger
    -0.06
    .newInstance
    -0.06
    POSITIVE LOGITS
     craft
    0.07
     Maiden
    0.07
    lis
    0.07
     quỹ
    0.07
    opis
    0.06
    loop
    0.06
    oma
    0.06
     loop
    0.06
    icans
    0.06
    ycz
    0.06
    Activations Density 0.011%

    No Known Activations