© 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. 56054
    Prev
    Next
    INDEX
    Explanations

    enthusiastic reactions and positive affirmations about experiences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Connective elements (conjunctions, pronouns, punctuation) that link ideas, particularly in informal descriptive writing about experiences, places, or events.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    asl
    -0.07
     McGr
    -0.06
    tility
    -0.05
     CHE
    -0.05
    andom
    -0.05
     purpose
    -0.05
    ube
    -0.05
     risk
    -0.05
    incess
    -0.05
     cracked
    -0.05
    POSITIVE LOGITS
    HORT
    0.08
    ãĥ¼ãĥª
    0.07
    osto
    0.07
    uja
    0.07
    UED
    0.07
    zek
    0.07
    лÑĥ
    0.07
    ãĥ¼ãĥĵ
    0.07
    BOSE
    0.07
    retim
    0.07
    Activations Density 0.049%

    No Known Activations