© 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. 2716
    Prev
    Next
    INDEX
    Explanations

    discussions around systemic structures and societal roles

    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
     intr
    -0.05
     Ven
    -0.05
    634
    -0.05
    ç«Ł
    -0.05
    unused
    -0.05
     suddenly
    -0.05
    688
    -0.05
     Par
    -0.05
    iat
    -0.05
     punct
    -0.05
    POSITIVE LOGITS
     continue
    0.25
     continued
    0.25
     continues
    0.23
    continue
    0.23
     continuing
    0.21
    	continue
    0.20
    continued
    0.20
    继ç»Ń
    0.20
     Continued
    0.19
    Continue
    0.19
    Activations Density 0.108%

    No Known Activations