© 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. 87215
    Prev
    Next
    INDEX
    Explanations

    references to versioning and release information in video games

    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
     infl
    -0.06
    visa
    -0.06
    bih
    -0.06
    .slim
    -0.06
    znam
    -0.06
    oucher
    -0.06
     opp
    -0.06
     Du
    -0.06
     Crist
    -0.06
    atorio
    -0.05
    POSITIVE LOGITS
    Ctrls
    0.08
    ãĥ³ãĤ°ãĥ«
    0.07
    MED
    0.07
    PCP
    0.07
    objs
    0.07
    pha
    0.06
    IRR
    0.06
    556
    0.06
    Bundle
    0.06
    Occurred
    0.06
    Activations Density 0.002%

    No Known Activations