© 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. 9-LLAMASCOPE-RES-131K
    11. 95535
    Prev
    Next
    INDEX
    Explanations

    URLs and related references in technical documentation

    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
    PathComponent
    -0.07
    年代
    -0.07
    cher
    -0.06
    ourd
    -0.06
    innacle
    -0.06
    chers
    -0.06
    uell
    -0.06
     SharedModule
    -0.06
    elist
    -0.06
     earnings
    -0.06
    POSITIVE LOGITS
     Cain
    0.07
    SSIP
    0.07
    orida
    0.06
    aren
    0.06
    SYS
    0.06
     verse
    0.06
    ainen
    0.06
    esian
    0.06
    AMI
    0.06
    åŀ
    0.06
    Activations Density 0.010%

    No Known Activations