© 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. 4518
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to software development

    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
    åIJĮåѦ
    -0.07
    .FloatTensor
    -0.07
    modifiable
    -0.07
    ëį°
    -0.07
    aku
    -0.06
    adÃŃ
    -0.06
    ï¼Įå°±æĺ¯
    -0.06
    aits
    -0.06
    oose
    -0.06
     jedno
    -0.06
    POSITIVE LOGITS
    0.11
    _TOO
    0.07
    ayd
    0.07
    780
    0.07
     Caucus
    0.06
    unded
    0.06
    WT
    0.06
    ï¼ħ
    0.06
    RS
    0.06
     Marsh
    0.06
    Activations Density 0.407%

    No Known Activations