© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80549
    Prev
    Next
    INDEX
    Explanations

    phrases related to being audible or acknowledged

    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
    indy
    -0.07
    ago
    -0.07
    ota
    -0.07
     Loose
    -0.07
    mt
    -0.06
    lý
    -0.06
    zed
    -0.06
    AINS
    -0.06
    åĬ¨çĶŁæĪIJ
    -0.06
    osta
    -0.06
    POSITIVE LOGITS
    ιÏĥÏĦο
    0.07
     culo
    0.07
    ancements
    0.06
     доÑģ
    0.06
     Separ
    0.06
    TexImage
    0.06
     ikt
    0.06
     createSelector
    0.06
    onne
    0.06
    ProcessEvent
    0.06
    Activations Density 0.006%

    No Known Activations