© 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. 73216
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the likelihood or necessity of future actions

    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
    istrovstvÃŃ
    -0.09
    éĢģæĸĻçĦ¡æĸĻ
    -0.07
    adal
    -0.07
     nues
    -0.07
    Äħż
    -0.07
    ingleton
    -0.07
    osg
    -0.07
    çĵľ
    -0.07
    abus
    -0.07
    ÛĮÛĮÙĨ
    -0.07
    POSITIVE LOGITS
    ll
    0.06
    ål
    0.06
    ake
    0.06
    838
    0.06
    Pitch
    0.06
     inher
    0.06
    ometer
    0.06
    i
    0.06
    c
    0.06
    cen
    0.06
    Activations Density 0.007%

    No Known Activations