© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 118025
    Prev
    Next
    INDEX
    Explanations

    references to image or illustration in textual content

    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
    ra
    -0.08
    shot
    -0.07
    rå
    -0.07
    rats
    -0.07
    essler
    -0.07
     Gameplay
    -0.06
    ly
    -0.06
    otify
    -0.06
    ouser
    -0.06
    rank
    -0.06
    POSITIVE LOGITS
     Exact
    0.07
    kept
    0.07
    ë§ģ
    0.07
    inus
    0.07
    QL
    0.06
    ocks
    0.06
    icho
    0.06
    Exact
    0.06
    íĦ
    0.06
    vÃŃc
    0.06
    Activations Density 0.005%

    No Known Activations