© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78045
    Prev
    Next
    INDEX
    Explanations

    special formatting characters and symbols

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

    Markup or formatting syntax tokens that signal the end of special content sections across different types of digital text.

    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
    agna
    -0.07
     Rencontre
    -0.06
    hani
    -0.06
    ãĥ¼ãĥij
    -0.06
    aceae
    -0.06
    .generic
    -0.06
    jee
    -0.06
     ModelState
    -0.06
    akk
    -0.06
    ilis
    -0.06
    POSITIVE LOGITS
    tlement
    0.07
    ãĢģ
    0.07
    rung
    0.07
    ç²ī
    0.06
    achat
    0.06
    овеÑĢ
    0.06
     Gross
    0.06
    enticator
    0.06
    URRED
    0.06
    teg
    0.06
    Activations Density 0.083%

    No Known Activations