© 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. 117850
    Prev
    Next
    INDEX
    Explanations

    references to entryways, openings, or access points in descriptions of properties

    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
    esini
    -0.07
     hete
    -0.07
    gram
    -0.07
    InView
    -0.06
    GRAM
    -0.06
    SSIP
    -0.06
    hta
    -0.06
    ساÙħ
    -0.06
    -medium
    -0.06
    enburg
    -0.06
    POSITIVE LOGITS
    sonian
    0.07
     ÑģÑİ
    0.07
     mod
    0.06
    seg
    0.06
     ActiveSupport
    0.06
    ÏĦεÏģ
    0.06
    ÃŃrk
    0.06
     Rarity
    0.06
    onto
    0.06
     Via
    0.06
    Activations Density 0.007%

    No Known Activations