© 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. 70534
    Prev
    Next
    INDEX
    Explanations

    references to management roles and investment companies

    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
    pii
    -0.08
    ijke
    -0.08
    -Allow
    -0.07
    urai
    -0.06
    úp
    -0.06
    zk
    -0.06
    dej
    -0.06
    elyn
    -0.06
     Pazar
    -0.06
    è¡
    -0.06
    POSITIVE LOGITS
    rog
    0.07
     Dodd
    0.07
    cl
    0.07
    clud
    0.06
    ÑĤÑĢо
    0.06
     Swe
    0.06
     jenter
    0.06
     Bryant
    0.06
     clue
    0.06
     Clay
    0.06
    Activations Density 0.001%

    No Known Activations