© 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. 123643
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" 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
    ãĥªãĥ¼ãĤº
    -0.08
    ÅĻi
    -0.07
     Spells
    -0.07
    nova
    -0.07
    onta
    -0.07
    .cms
    -0.07
    odge
    -0.07
    ообÑĢаз
    -0.07
     Agricult
    -0.07
    oker
    -0.06
    POSITIVE LOGITS
     we
    0.07
     part
    0.06
    aph
    0.06
    esters
    0.06
     continue
    0.06
     hopefully
    0.06
     nto
    0.06
    continue
    0.06
     vel
    0.06
    -valu
    0.06
    Activations Density 0.015%

    No Known Activations