© 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. 15-LLAMASCOPE-RES-131K
    11. 88208
    Prev
    Next
    INDEX
    Explanations

    occurrences of comment formatting and annotations 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
    quine
    -0.07
    zin
    -0.07
     imp
    -0.07
    елÑİ
    -0.07
    anas
    -0.07
    imd
    -0.07
     mdi
    -0.07
    reon
    -0.06
    ijken
    -0.06
    ifar
    -0.06
    POSITIVE LOGITS
     Rit
    0.06
    ãĥªãĤ¹
    0.06
     Pied
    0.06
    ãĥ¼ãĥĬ
    0.06
     Opportunity
    0.06
     Burb
    0.06
    879
    0.05
    oney
    0.05
    аж
    0.05
    ritos
    0.05
    Activations Density 0.001%

    No Known Activations