© 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. 17-LLAMASCOPE-RES-131K
    11. 74288
    Prev
    Next
    INDEX
    Explanations

    financial contributions and grants to various organizations or causes

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

    Text elements that represent structured metadata in web content, including donation information with locations and amounts, timestamps, indexing symbols, and formatting punctuation.

    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
    eso
    -0.08
    Refs
    -0.08
    esa
    -0.07
     Bilim
    -0.07
    dux
    -0.07
    ì°©
    -0.07
    ROTO
    -0.07
    .answers
    -0.06
    _extended
    -0.06
     milyar
    -0.06
    POSITIVE LOGITS
    .jsoup
    0.06
    empt
    0.06
    gars
    0.06
    aget
    0.06
    apple
    0.06
    @nate
    0.06
    abant
    0.06
    folk
    0.06
     logically
    0.06
     classics
    0.06
    Activations Density 0.015%

    No Known Activations