© 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 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. 78379
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and other indicators of significance, such as first or only

    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
    Æ°Æ¡ng
    -0.07
    uli
    -0.06
    appropriate
    -0.06
    zell
    -0.06
     Brewer
    -0.06
    adol
    -0.06
    adt
    -0.06
    ium
    -0.06
    edReader
    -0.06
    edList
    -0.06
    POSITIVE LOGITS
     son
    0.08
     god
    0.07
    #=
    0.07
     man
    0.07
     archetype
    0.06
     sez
    0.06
     father
    0.06
     siz
    0.06
    ocab
    0.06
     reve
    0.06
    Activations Density 0.020%

    No Known Activations