© 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. 62076
    Prev
    Next
    INDEX
    Explanations

    terms related to medical residency and education

    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
    IER
    -0.08
    iola
    -0.07
    ãĥ¼ãĥ«ãĥī
    -0.07
    ieres
    -0.06
    kode
    -0.06
    defgroup
    -0.06
     Nicholson
    -0.06
    ká
    -0.06
    razier
    -0.06
    thritis
    -0.06
    POSITIVE LOGITS
    /train
    0.07
    enko
    0.07
     rotations
    0.07
    _Display
    0.06
    ROTO
    0.06
    -training
    0.06
     Rotation
    0.06
    eyi
    0.06
    ends
    0.06
    roke
    0.06
    Activations Density 0.012%

    No Known Activations