© 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. 81966
    Prev
    Next
    INDEX
    Explanations

    references to educational leadership and positions

    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
    Łèĥ½
    -0.09
    ̧
    -0.08
    AMS
    -0.07
    ìĦłìĿĦ
    -0.07
    æį·
    -0.07
    íį¼
    -0.07
     iParam
    -0.07
    iz
    -0.06
    ÎŃÏģα
    -0.06
    ìĦł
    -0.06
    POSITIVE LOGITS
     Citizens
    0.06
     Local
    0.06
    ende
    0.06
     chairman
    0.06
     Men
    0.06
     booster
    0.06
    ~=
    0.06
     BOOST
    0.06
    neh
    0.06
    adil
    0.06
    Activations Density 0.018%

    No Known Activations