© 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. 70150
    Prev
    Next
    INDEX
    Explanations

    the word "as" used 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
    enko
    -0.06
    oller
    -0.06
     Rip
    -0.06
    ysz
    -0.06
    bens
    -0.06
    beth
    -0.06
     Platt
    -0.06
    543
    -0.06
     normal
    -0.05
     rip
    -0.05
    POSITIVE LOGITS
    以åıĬ
    0.08
    ãģĦãĤĦ
    0.08
    ï¼Į以åıĬ
    0.07
    Ø·ÙĦ
    0.07
    umes
    0.07
    (éĩij
    0.07
     samt
    0.07
    httpClient
    0.07
    xsd
    0.07
    iego
    0.07
    Activations Density 0.042%

    No Known Activations