© 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. 16533
    Prev
    Next
    INDEX
    Explanations

    website addresses or email formatting

    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
    inke
    -0.07
     assembly
    -0.06
    ards
    -0.06
    ippi
    -0.06
     binary
    -0.05
     ket
    -0.05
     echo
    -0.05
    bai
    -0.05
     labor
    -0.05
    atra
    -0.05
    POSITIVE LOGITS
    икÑĥ
    0.08
     Collider
    0.07
    εδ
    0.07
    tur
    0.07
    ENTER
    0.07
     OTHERWISE
    0.07
    riages
    0.07
    -strokes
    0.07
    ixe
    0.07
    ãĥ³ãĥĸ
    0.07
    Activations Density 0.004%

    No Known Activations