© 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. 120528
    Prev
    Next
    INDEX
    Explanations

    programming structure annotations or keywords

    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
    ended
    -0.07
    ibase
    -0.07
    ervers
    -0.07
    /../
    -0.07
    ervo
    -0.06
    apped
    -0.06
     Outer
    -0.06
    ibu
    -0.06
    /msg
    -0.06
    år
    -0.06
    POSITIVE LOGITS
    olesale
    0.06
    Unmount
    0.06
    589
    0.06
     Fro
    0.06
    quam
    0.06
    byn
    0.06
    太éĥİ
    0.06
    bakan
    0.06
     pron
    0.06
    uvwxyz
    0.05
    Activations Density 0.001%

    No Known Activations