© 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. 4615
    Prev
    Next
    INDEX
    Explanations

    references to academic collaboration and mutual obligations

    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
    orra
    -0.07
    obili
    -0.07
    urai
    -0.07
    igh
    -0.06
    orang
    -0.06
    umb
    -0.06
    ettel
    -0.06
    alu
    -0.06
    öff
    -0.06
     Silva
    -0.06
    POSITIVE LOGITS
     respectively
    0.14
     respective
    0.14
    对æĸ¹
    0.12
     opposite
    0.11
    åı¦ä¸Ģ
    0.10
     either
    0.09
     ÑģооÑĤвеÑĤ
    0.08
     Either
    0.08
     пÑĢоÑĤивоп
    0.08
    Either
    0.08
    Activations Density 0.016%

    No Known Activations