© 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. 86148
    Prev
    Next
    INDEX
    Explanations

    various forms of digital media or technological applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Website headlines, article titles, or clickable navigation elements that serve as content links on webpages, often appearing in list format.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    itters
    -0.08
    رÙĩ
    -0.07
    /animate
    -0.07
    irket
    -0.07
    ampa
    -0.06
    ÏĦÏĤ
    -0.06
    Ã¤ÃŁ
    -0.06
    emic
    -0.06
    ScreenState
    -0.06
    ynch
    -0.06
    POSITIVE LOGITS
    urm
    0.07
     plate
    0.07
    kus
    0.07
    uur
    0.06
    losed
    0.06
    ÙħØ©
    0.06
    strar
    0.06
    طب
    0.06
    hlen
    0.06
     gener
    0.06
    Activations Density 0.009%

    No Known Activations