© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42778
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "The" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    creds
    -0.07
     nackte
    -0.07
    Clickable
    -0.07
    ght
    -0.07
    htable
    -0.07
    .AI
    -0.07
    ilated
    -0.07
    (çģ«
    -0.07
     Scalars
    -0.07
    áy
    -0.07
    POSITIVE LOGITS
    uling
    0.06
    Ñijн
    0.06
    ardon
    0.06
    tas
    0.06
    riott
    0.06
    iÃŁ
    0.05
     aaa
    0.05
    oric
    0.05
    apse
    0.05
    eron
    0.05
    Activations Density 0.001%

    No Known Activations