© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61672
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts, particularly emphasizing its repeated or significant appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    imu
    -0.07
    .jd
    -0.06
    ::__
    -0.06
    anco
    -0.06
    plx
    -0.06
    osi
    -0.06
    inizi
    -0.06
    &uuml
    -0.06
    adu
    -0.06
    Readable
    -0.06
    POSITIVE LOGITS
    same
    0.08
     ones
    0.08
     same
    0.08
    gement
    0.08
     SAME
    0.07
    ieber
    0.06
    ologically
    0.06
    abelle
    0.06
    Same
    0.06
    -ÑĤо
    0.06
    Activations Density 0.043%

    No Known Activations