© 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. 87485
    Prev
    Next
    INDEX
    Explanations

    comparative phrases, particularly those involving the word "than"

    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
    ruž
    -0.07
    hibit
    -0.07
    lamaya
    -0.07
    gom
    -0.07
    CUS
    -0.07
    ÙĦÛĮت
    -0.06
    amura
    -0.06
    qli
    -0.06
    ué
    -0.06
    ãĥ¼ãĥ
    -0.06
    POSITIVE LOGITS
    omen
    0.08
    ictions
    0.06
    amento
    0.06
    .vs
    0.06
     Hindered
    0.06
    ekt
    0.06
    ynet
    0.06
    ĭ
    0.06
     long
    0.05
    icina
    0.05
    Activations Density 0.001%

    No Known Activations