Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43584
    Prev
    Next
    INDEX
    Explanations

    references to agricultural organizations and related entities

    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
    elay
    -0.06
    ypse
    -0.06
    akin
    -0.06
    icky
    -0.06
    ylon
    -0.06
    jak
    -0.06
    asion
    -0.06
    _SLAVE
    -0.06
    aviolet
    -0.06
    .nodeName
    -0.06
    POSITIVE LOGITS
    OST
    0.10
    IMER
    0.09
    OLE
    0.09
    OUN
    0.09
    IRR
    0.09
    O
    0.08
    ostat
    0.08
    ECTOR
    0.08
    STAT
    0.08
    IRM
    0.08
    Activations Density 0.004%

    No Known Activations