© 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. 125578
    Prev
    Next
    INDEX
    Explanations

    key financial terms and discussions surrounding economic data

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

    Short character sequences (typically 2-3 letters) that represent the beginning of words used as identifiers, tags, or prefixes in digital content systems.

    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
     Reyn
    -0.06
    c
    -0.06
    haft
    -0.06
     CircularProgress
    -0.06
    yntax
    -0.06
    оÑģÑĮ
    -0.06
    dehyde
    -0.06
     ap
    -0.05
    aternity
    -0.05
    i
    -0.05
    POSITIVE LOGITS
    éĢģæĸĻçĦ¡æĸĻ
    0.08
    ebek
    0.07
    rire
    0.07
    ioni
    0.07
    iple
    0.07
    تÙĥ
    0.07
    -placeholder
    0.07
    alles
    0.07
    .Void
    0.07
    анÑģи
    0.07
    Activations Density 0.066%

    No Known Activations