© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89650
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and versioning information

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ffi
    -0.07
    iji
    -0.07
    usted
    -0.06
    оÑģÑĤаÑĤ
    -0.06
    ifax
    -0.06
     erg
    -0.06
    bow
    -0.06
    usting
    -0.05
     extinction
    -0.05
    æľīåħ³
    -0.05
    POSITIVE LOGITS
    	Version
    0.08
    ëĿ½
    0.07
     اÙħر
    0.07
    ILED
    0.07
    ãĥĥãĤ·ãĥ¥
    0.07
    BU
    0.07
    frauen
    0.06
     WARRANT
    0.06
    (--
    0.06
    $core
    0.06
    Activations Density 0.004%

    No Known Activations