© 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. 27167
    Prev
    Next
    INDEX
    Explanations

    references to different groups of people and their diverse backgrounds or identities

    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
    aign
    -0.09
    ighton
    -0.09
    еÑĢÑĪ
    -0.08
    oire
    -0.07
    olars
    -0.07
    readcr
    -0.07
    ñas
    -0.07
    uilt
    -0.07
    PÅĻi
    -0.07
    GuidId
    -0.07
    POSITIVE LOGITS
     whom
    0.10
     backgrounds
    0.09
     background
    0.08
     ages
    0.07
     who
    0.07
    ãĥ£
    0.07
     Background
    0.06
    Background
    0.06
     Mondays
    0.06
    background
    0.06
    Activations Density 0.142%

    No Known Activations