© 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 EvalsExportsinterp-engineNEWAPI 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. 86877
    Prev
    Next
    INDEX
    Explanations

    words reflecting emotional states or qualities related to music and relationships

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

    Tokens that appear at ends of words where they can act as word endings or suffixes, typically in contexts where they're part of key terms or relevant information.

    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
    baugh
    -0.07
    ench
    -0.06
    ű
    -0.06
    íĬľ
    -0.06
     conver
    -0.06
    eus
    -0.06
    rid
    -0.06
    ãĥ
    -0.06
    ENCH
    -0.06
     ancest
    -0.06
    POSITIVE LOGITS
    ä¸įäºĨ
    0.08
    vais
    0.07
    jal
    0.07
    edBy
    0.07
    TEGER
    0.07
    arih
    0.06
    ÏĦεί
    0.06
    erts
    0.06
    LARI
    0.06
    amar
    0.06
    Activations Density 0.077%

    No Known Activations