© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75807
    Prev
    Next
    INDEX
    Explanations

    references to receiving updates and notifications

    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
    iji
    -0.07
    erp
    -0.06
    mong
    -0.06
    pit
    -0.06
    andr
    -0.06
    imits
    -0.06
    essel
    -0.06
    æ²Ļ
    -0.06
    ervo
    -0.06
    ix
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    uzey
    0.08
    axed
    0.07
     Ort
    0.07
     about
    0.07
    /rem
    0.07
    about
    0.07
     throughout
    0.07
    afil
    0.06
    lsa
    0.06
    Activations Density 0.003%

    No Known Activations