© 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. 4009
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts

    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
    -0.07
    oze
    -0.07
     Ball
    -0.06
    icc
    -0.05
     wi
    -0.05
     Crack
    -0.05
    245
    -0.05
     (
    -0.05
     Pair
    -0.05
    .Side
    -0.05
    POSITIVE LOGITS
     consequences
    0.08
    .scalablytyped
    0.08
     cul
    0.07
     consequence
    0.07
    ragon
    0.07
     situation
    0.07
    Instances
    0.07
    -urlencoded
    0.07
    ÑģÑĤанов
    0.07
     lucky
    0.07
    Activations Density 0.034%

    No Known Activations