© 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. 69805
    Prev
    Next
    INDEX
    Explanations

    expressions of strong agreement or emphasis

    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
    ardin
    -0.07
     PARTICULAR
    -0.07
    zelf
    -0.07
    rey
    -0.07
    orial
    -0.06
     جÙĩ
    -0.06
    soever
    -0.06
    наÑĩе
    -0.06
    nal
    -0.06
    hta
    -0.06
    POSITIVE LOGITS
    جة
    0.06
    577
    0.06
    fl
    0.06
    aney
    0.06
    atom
    0.06
    SSF
    0.06
    :::::::
    0.06
    tml
    0.06
    624
    0.06
    ymb
    0.05
    Activations Density 0.005%

    No Known Activations