© 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. 54862
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence of conditional or causal relationships

    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
    _NR
    -0.07
    .toolbox
    -0.07
    _ISO
    -0.07
    @js
    -0.07
    oyal
    -0.07
    UIImagePickerController
    -0.07
    å¾
    -0.07
    ãĥ³ãĥĸ
    -0.07
     crossorigin
    -0.07
     dva
    -0.07
    POSITIVE LOGITS
     only
    0.08
     later
    0.08
     none
    0.07
     neither
    0.07
     no
    0.07
    later
    0.07
    urm
    0.06
     nothing
    0.06
     fine
    0.06
     basically
    0.06
    Activations Density 0.031%

    No Known Activations