© 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. 39530
    Prev
    Next
    INDEX
    Explanations

    punctuation or special characters

    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
    asso
    -0.08
    rew
    -0.08
    rael
    -0.07
    ihan
    -0.07
    REW
    -0.07
    Ä±ÅŁÄ±
    -0.07
    ãĤ·ãĥ¼
    -0.06
    erson
    -0.06
    638
    -0.06
    rax
    -0.06
    POSITIVE LOGITS
     pits
    0.07
    teÅŁ
    0.06
    ivr
    0.06
    toolbox
    0.06
     Dal
    0.06
    à¥ģष
    0.06
    uckets
    0.06
    åĿĬ
    0.05
     Schwarz
    0.05
     Ig
    0.05
    Activations Density 0.002%

    No Known Activations