© 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. 4150
    Prev
    Next
    INDEX
    Explanations

    terms related to database management systems and programming

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

    Character sequences within technical terms, code snippets, or proper names that represent meaningful linguistic subunits in specialized contexts.

    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
    iller
    -0.07
    inding
    -0.07
    !
    -0.06
     to
    -0.06
    azy
    -0.06
    urge
    -0.06
    toc
    -0.05
    Âł
    -0.05
    ://
    -0.05
    lak
    -0.05
    POSITIVE LOGITS
    ---</
    0.09
    ÑĢоÑĦ
    0.08
    ruba
    0.08
    afone
    0.08
    'gc
    0.08
    ÑĤеÑģÑĮ
    0.08
    ----</
    0.08
    (TM
    0.08
    /WebAPI
    0.08
    ़
    0.08
    Activations Density 0.057%

    No Known Activations