© 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. 88696
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the word "use" and its context in relation to various subjects

    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
    ãĤ¤ãĤº
    -0.06
    shan
    -0.06
    gh
    -0.06
    emie
    -0.06
    rk
    -0.06
    ãĥIJãĥ¼
    -0.06
    nder
    -0.05
     he
    -0.05
    ntl
    -0.05
    thouse
    -0.05
    POSITIVE LOGITS
    ings
    0.08
    able
    0.08
    age
    0.08
    iley
    0.07
    ages
    0.07
    ableObject
    0.07
    .nlm
    0.07
    ingen
    0.07
    ability
    0.07
    ivet
    0.07
    Activations Density 0.013%

    No Known Activations