© 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. 1867
    Prev
    Next
    INDEX
    Explanations

    structured programming terminology and object-oriented concepts

    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
    zek
    -0.06
    ¹
    -0.06
     litter
    -0.06
     nouve
    -0.06
     ÑĥÑħ
    -0.06
    pth
    -0.06
    	fflush
    -0.06
    vap
    -0.06
     gang
    -0.06
    monic
    -0.06
    POSITIVE LOGITS
    wers
    0.08
    aN
    0.07
    avo
    0.07
    uden
    0.07
    ucz
    0.07
     Ire
    0.07
     Ngb
    0.06
    Fuse
    0.06
    наÑħ
    0.06
     ENTITY
    0.06
    Activations Density 0.000%

    No Known Activations