© 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. 28292
    Prev
    Next
    INDEX
    Explanations

    present tense forms of the verb "to be" and related attributes

    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
     new
    -0.08
    ãĥ¥
    -0.07
     developing
    -0.06
    нив
    -0.06
    /=
    -0.06
    INI
    -0.06
    nt
    -0.06
     stat
    -0.06
     Ike
    -0.06
    CEE
    -0.06
    POSITIVE LOGITS
    antic
    0.07
    .Foundation
    0.07
    mada
    0.07
    agg
    0.07
    apol
    0.07
    iname
    0.07
    lingen
    0.07
    dlg
    0.07
    zs
    0.07
    amb
    0.07
    Activations Density 0.033%

    No Known Activations