© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 130013
    Prev
    Next
    INDEX
    Explanations

    verbs associated with popularity or frequency of use

    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
    berger
    -0.08
    nul
    -0.07
    izr
    -0.07
    λικ
    -0.07
    inton
    -0.07
    ãģıãĤī
    -0.07
    angl
    -0.07
    erva
    -0.07
    kol
    -0.07
    agini
    -0.06
    POSITIVE LOGITS
    -about
    0.10
    -around
    0.08
    among
    0.08
     among
    0.07
     itemCount
    0.07
     scrim
    0.06
    edBy
    0.06
     ÑģÑĢеди
    0.06
    /view
    0.06
    -after
    0.06
    Activations Density 0.010%

    No Known Activations