© 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. 84573
    Prev
    Next
    INDEX
    Explanations

    names of people and their associated identities or titles

    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
    t
    -0.07
    acht
    -0.06
     min
    -0.06
    enci
    -0.06
     sus
    -0.06
    Sus
    -0.05
    odb
    -0.05
    avr
    -0.05
    ijkstra
    -0.05
     Sus
    -0.05
    POSITIVE LOGITS
    patrick
    0.10
    metis
    0.08
    bud
    0.07
    alara
    0.07
     بÙĪدÙĨ
    0.07
     plá
    0.07
    Äįin
    0.07
    slow
    0.07
    .messaging
    0.07
     Ø®ÙĪر
    0.07
    Activations Density 0.021%

    No Known Activations