© 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. 61800
    Prev
    Next
    INDEX
    Explanations

    references to various educational and professional associations

    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
    anten
    -0.07
    βο
    -0.07
    è¦ļ
    -0.07
    porto
    -0.07
    \Common
    -0.06
    ãi
    -0.06
    ItemAt
    -0.06
     Jerseys
    -0.06
    _lab
    -0.06
    olio
    -0.06
    POSITIVE LOGITS
     baths
    0.06
    aklı
    0.06
    .sig
    0.06
     grav
    0.06
     ped
    0.06
    ederation
    0.06
     conc
    0.06
    igung
    0.06
     passage
    0.05
    bble
    0.05
    Activations Density 0.049%

    No Known Activations