© 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. 42204
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "mit" and related contextual phrases

    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
    eries
    -0.07
    emy
    -0.06
    vere
    -0.06
    ides
    -0.06
     Hem
    -0.06
    parallel
    -0.06
     Tro
    -0.06
    eme
    -0.06
    haft
    -0.06
    s
    -0.06
    POSITIVE LOGITS
    red
    0.08
     Intermediate
    0.07
    uten
    0.07
    inel
    0.07
    ropolis
    0.07
    ERCHANT
    0.07
    .ejb
    0.07
    ÑĩиÑģ
    0.07
    ÅĻ
    0.07
    lesh
    0.07
    Activations Density 0.002%

    No Known Activations