© 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. 28750
    Prev
    Next
    INDEX
    Explanations

    references to academic or professional qualifications and roles

    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
    deen
    -0.07
     Sup
    -0.07
    .rel
    -0.07
    ÏĥÏĢ
    -0.07
    emachine
    -0.07
     کاربر
    -0.07
    assa
    -0.07
     Grass
    -0.06
    -*-
    -0.06
    anked
    -0.06
    POSITIVE LOGITS
     contribution
    0.08
     others
    0.07
     presence
    0.06
     other
    0.06
     EITHER
    0.06
     contributions
    0.06
     involvement
    0.06
    others
    0.06
     written
    0.06
     comm
    0.06
    Activations Density 0.006%

    No Known Activations