© 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 EvalsExportsAPI 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. 78514
    Prev
    Next
    INDEX
    Explanations

    words related to entertainment or humor

    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
    ODO
    -0.07
    ricks
    -0.07
     Dude
    -0.07
    iks
    -0.06
    odore
    -0.06
    odo
    -0.06
    indi
    -0.06
    kyt
    -0.06
    à¸ģล
    -0.06
    ikip
    -0.06
    POSITIVE LOGITS
     THIS
    0.09
     this
    0.09
    this
    0.08
     thì
    0.08
     hãy
    0.08
    THIS
    0.08
    (this
    0.07
     questo
    0.07
    	this
    0.07
    ,this
    0.07
    Activations Density 0.032%

    No Known Activations