© 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. 98185
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and semicolons in code snippets

    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
    ILD
    -0.07
    azzi
    -0.07
    agle
    -0.07
    agne
    -0.07
    InstanceState
    -0.07
    lain
    -0.06
    داد
    -0.06
    enna
    -0.06
    ód
    -0.06
    -append
    -0.06
    POSITIVE LOGITS
    लà¤Ĺ
    0.06
    ubit
    0.06
    amework
    0.06
     Kee
    0.06
    atron
    0.06
    éĬ
    0.06
     KING
    0.06
    {:
    0.06
     ï¿¥
    0.06
    ãĤŃãĥ³ãĤ°
    0.06
    Activations Density 0.003%

    No Known Activations