© 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. 71376
    Prev
    Next
    INDEX
    Explanations

    references to medical institutions and research studies

    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
    spb
    -0.07
    urtles
    -0.07
    inho
    -0.07
    .GetProperty
    -0.06
    stderr
    -0.06
    ìĨį
    -0.06
    fdc
    -0.06
    项
    -0.06
     Supported
    -0.06
    éĭ¼
    -0.06
    POSITIVE LOGITS
     slideshow
    0.07
     Script
    0.07
    pto
    0.06
    edo
    0.06
    .rd
    0.06
    wich
    0.06
    bos
    0.06
    assed
    0.06
    assi
    0.06
    altar
    0.06
    Activations Density 0.010%

    No Known Activations