© 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 EvalsExportsinterp-engineNEWAPI 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. 4939
    Prev
    Next
    INDEX
    Explanations

    technical discussions about coding and data conversion

    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
     dri
    -0.07
    peri
    -0.06
     Opcode
    -0.06
    ç©¿
    -0.06
    ì»
    -0.06
    iliz
    -0.06
    achs
    -0.06
    -inline
    -0.06
    unique
    -0.06
    ether
    -0.06
    POSITIVE LOGITS
    =UTF
    0.07
    .native
    0.07
    olang
    0.07
    :NSUTF
    0.07
    .encoding
    0.07
    babel
    0.07
    ENSION
    0.07
    /Area
    0.06
    åįĩ
    0.06
    059
    0.06
    Activations Density 0.005%

    No Known Activations