© 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 EvalsExportsAPI 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. 89094
    Prev
    Next
    INDEX
    Explanations

    references to academic initiatives and institutional collaborations

    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
    ë°ľ
    -0.08
    lea
    -0.07
     Dün
    -0.07
    igham
    -0.07
    ensa
    -0.07
    ocup
    -0.07
    даÑĤ
    -0.07
    isme
    -0.06
    ocumented
    -0.06
    phia
    -0.06
    POSITIVE LOGITS
    856
    0.07
     research
    0.07
     Research
    0.07
     Prov
    0.07
    Prov
    0.06
    968
    0.06
     prov
    0.06
     clusters
    0.06
    935
    0.06
    kt
    0.06
    Activations Density 0.019%

    No Known Activations