© 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. 9-LLAMASCOPE-RES-131K
    11. 98278
    Prev
    Next
    INDEX
    Explanations

    concepts that emphasize focus or emphasis on specific topics

    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
     shalt
    -0.07
    rell
    -0.06
     же
    -0.06
    utor
    -0.06
    aters
    -0.06
    avors
    -0.06
    onta
    -0.06
    389
    -0.06
    ato
    -0.06
    aku
    -0.06
    POSITIVE LOGITS
    okrat
    0.07
    OutOfBounds
    0.07
    manship
    0.07
    lix
    0.07
    ÑĥÑĩа
    0.06
     Kawasaki
    0.06
     æIJ
    0.06
    bserv
    0.06
    ÙijÙĩ
    0.06
    ASM
    0.06
    Activations Density 0.019%

    No Known Activations