© 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. 119268
    Prev
    Next
    INDEX
    Explanations

    structural or syntactical elements in a code or technical document

    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
    avig
    -0.08
    #create
    -0.08
    retty
    -0.07
    	Copyright
    -0.07
    iert
    -0.07
     ngh
    -0.07
    noinspection
    -0.07
    cht
    -0.06
    .Chart
    -0.06
     имÑĥ
    -0.06
    POSITIVE LOGITS
     tide
    0.06
    aley
    0.06
     ${({
    0.06
    VERRIDE
    0.05
    ase
    0.05
    iese
    0.05
    reeze
    0.05
    280
    0.05
     Kle
    0.05
    ardi
    0.05
    Activations Density 0.009%

    No Known Activations