© 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. 118825
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    illard
    -0.07
    fare
    -0.06
    sumer
    -0.06
     fat
    -0.06
    ington
    -0.06
    erver
    -0.06
    's
    -0.06
    fat
    -0.06
     Fat
    -0.06
     IDs
    -0.06
    POSITIVE LOGITS
    ãĥªãĤ«
    0.08
    .PER
    0.07
    RIX
    0.07
    upil
    0.07
    EIF
    0.07
     domácÃŃ
    0.07
    .sess
    0.07
     ..."↵↵
    0.07
    ataire
    0.07
    eba
    0.07
    Activations Density 0.000%

    No Known Activations