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

    Neuronpedia

    Jacobian LensNEW
    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. 93743
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names

    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
    istrovstvÃŃ
    -0.09
    senal
    -0.08
    antro
    -0.07
    .mybatisplus
    -0.07
    using
    -0.07
    ollectors
    -0.07
    etheless
    -0.07
    ryfall
    -0.07
    apon
    -0.07
    puties
    -0.07
    POSITIVE LOGITS
    #ad
    0.10
    овиÑĩ
    0.09
    ̣
    0.08
     doz
    0.08
    álo
    0.08
     âĹ
    0.08
    ìĤ¬ìĿĺ
    0.08
     enr
    0.08
     rall
    0.08
     consc
    0.08
    Activations Density 0.994%

    No Known Activations