© 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. 15-LLAMASCOPE-RES-131K
    11. 86892
    Prev
    Next
    INDEX
    Explanations

    phrases related to usage and functionality of processes or objects

    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
    ancement
    -0.06
    rig
    -0.06
     otherwise
    -0.06
     Sylv
    -0.06
     even
    -0.06
     tears
    -0.06
     Cherry
    -0.06
    emo
    -0.06
     cherry
    -0.05
     Otherwise
    -0.05
    POSITIVE LOGITS
    ãĥ
    0.07
     EITHER
    0.07
    ä¸ĢæŃ¥
    0.07
    iyon
    0.07
    .onViewCreated
    0.07
     genellikle
    0.07
    ä¸Ģç§į
    0.07
    Bindable
    0.07
    trl
    0.07
     tạm
    0.07
    Activations Density 0.027%

    No Known Activations