© 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. 98317
    Prev
    Next
    INDEX
    Explanations

    terms related to educational programs and academic degrees

    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
     middle
    -0.06
     Surround
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    omm
    -0.06
    idd
    -0.06
    udu
    -0.06
    adu
    -0.06
     Ste
    -0.06
     surrounding
    -0.05
    uguay
    -0.05
    POSITIVE LOGITS
     hete
    0.08
     kla
    0.07
    ervo
    0.07
    opoulos
    0.07
     wiÄĻc
    0.07
     parten
    0.07
    عÙĬ
    0.07
    ilis
    0.07
    -scrollbar
    0.07
    atter
    0.07
    Activations Density 0.018%

    No Known Activations