© 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. 86853
    Prev
    Next
    INDEX
    Explanations

    phrases related to participation in various services or activities, particularly those involving education, investments, and secure transactions

    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
    olk
    -0.07
     till
    -0.07
    ampton
    -0.06
    meaning
    -0.06
     Till
    -0.06
    Intersection
    -0.06
    fon
    -0.06
    ãĤ¤ãĥ¤
    -0.06
    exus
    -0.06
     until
    -0.06
    POSITIVE LOGITS
     versus
    0.11
     instead
    0.11
     vs
    0.10
    instead
    0.10
     statt
    0.09
     вмеÑģÑĤ
    0.09
    vs
    0.09
     Instead
    0.09
    Instead
    0.09
     rather
    0.08
    Activations Density 0.027%

    No Known Activations