© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119721
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that contain a high frequency of punctuation or non-verbal characters

    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
    ehler
    -0.08
    ninger
    -0.07
    ãĥĭãĤ¢
    -0.07
    ertest
    -0.07
    ilter
    -0.07
    ÑıÑħ
    -0.07
    ayah
    -0.07
    avel
    -0.07
    ibo
    -0.07
    urus
    -0.07
    POSITIVE LOGITS
     Shir
    0.06
    mods
    0.06
     kin
    0.06
     Mant
    0.06
     vess
    0.06
    大人
    0.05
     Manip
    0.05
    flo
    0.05
    Margins
    0.05
     Die
    0.05
    Activations Density 0.001%

    No Known Activations