© 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 EvalsExportsAPI 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. 56155
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and semicolons in code

    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
    reib
    -0.07
    alles
    -0.07
     å¼
    -0.07
    012
    -0.07
    CU
    -0.06
    ãĥ¼ãĥª
    -0.06
    ILLE
    -0.06
    allon
    -0.06
    vac
    -0.06
    lider
    -0.06
    POSITIVE LOGITS
    ovel
    0.06
     Robbins
    0.06
    irit
    0.06
    279
    0.06
    tvrt
    0.06
    aks
    0.06
    %"><
    0.06
    ouch
    0.06
    éħ
    0.05
     ÐĶив
    0.05
    Activations Density 0.000%

    No Known Activations