© 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. 90290
    Prev
    Next
    INDEX
    Explanations

    recognition of achievements in students

    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
    azzi
    -0.08
    ød
    -0.08
    aticon
    -0.07
    ingroup
    -0.07
    .tpl
    -0.07
    ẩu
    -0.07
    ManagerInterface
    -0.07
    mdb
    -0.07
     Äįlán
    -0.07
    ноз
    -0.06
    POSITIVE LOGITS
     Mrs
    0.07
    osten
    0.06
    Mrs
    0.06
     extr
    0.06
     locally
    0.06
    pha
    0.05
    973
    0.05
    ymb
    0.05
     selected
    0.05
     Detail
    0.05
    Activations Density 0.023%

    No Known Activations