© 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. 74106
    Prev
    Next
    INDEX
    Explanations

    phrases describing packaging and containment

    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
    -fontawesome
    -0.07
    beer
    -0.06
    984
    -0.06
     Couch
    -0.06
    adh
    -0.06
    isque
    -0.06
    zzle
    -0.05
    ศร
    -0.05
     fauc
    -0.05
    -transform
    -0.05
    POSITIVE LOGITS
     containers
    0.08
     container
    0.07
    åİ»äºĨ
    0.07
    LAY
    0.07
    ÑĤож
    0.07
     boxes
    0.06
    ÏĦαν
    0.06
    _NPC
    0.06
    iku
    0.06
     packaging
    0.06
    Activations Density 0.035%

    No Known Activations