© 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. 17841
    Prev
    Next
    INDEX
    Explanations

    discussions about definitions and classifications within literature and culture

    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
    rieve
    -0.07
    vailability
    -0.07
    sko
    -0.06
     imag
    -0.06
    ÑĢеп
    -0.06
    eÅŁ
    -0.06
    cke
    -0.06
    iams
    -0.06
    abant
    -0.06
    наÑĩе
    -0.06
    POSITIVE LOGITS
     whether
    0.16
    whether
    0.14
    æĺ¯åIJ¦
    0.14
     Whether
    0.13
    Whether
    0.12
     WHETHER
    0.12
     æĺ¯åIJ¦
    0.12
     should
    0.11
     Should
    0.11
    Should
    0.10
    Activations Density 0.081%

    No Known Activations