© 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. 31087
    Prev
    Next
    INDEX
    Explanations

    the verb "are" and its variations to indicate existence or presence

    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
    elyn
    -0.07
     bilgi
    -0.07
    enaire
    -0.07
    .Slf
    -0.07
     informatie
    -0.07
    ÙĬات
    -0.07
    ãĥ«ãĥĪ
    -0.07
    448
    -0.07
    271
    -0.07
    ÑĤаж
    -0.07
    POSITIVE LOGITS
     two
    0.10
     few
    0.10
     several
    0.07
     many
    0.07
     three
    0.07
    few
    0.07
     certain
    0.07
    nt
    0.06
     fewer
    0.06
     no
    0.06
    Activations Density 0.044%

    No Known Activations