© 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. 72450
    Prev
    Next
    INDEX
    Explanations

    emotionally charged phrases related to mockery and distress

    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
    undy
    -0.06
    çľī
    -0.06
    .Sin
    -0.06
    urgeon
    -0.06
    upy
    -0.06
    /trunk
    -0.06
     YaÅŁ
    -0.06
    ÏĦÏģι
    -0.06
    idge
    -0.06
    lip
    -0.06
    POSITIVE LOGITS
    éĤ
    0.07
    eyer
    0.07
    igest
    0.06
     navr
    0.06
    .tc
    0.06
     refl
    0.06
     Shaft
    0.06
     cess
    0.06
     Interpret
    0.06
    unic
    0.06
    Activations Density 0.004%

    No Known Activations