© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15691
    Prev
    Next
    INDEX
    Explanations

    connections and contrasts between various elements or themes

    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
    arp
    -0.08
    antino
    -0.07
    otti
    -0.06
    hausen
    -0.06
    idunt
    -0.06
    ym
    -0.06
    worthy
    -0.06
    cul
    -0.06
    aska
    -0.06
    ERA
    -0.06
    POSITIVE LOGITS
     entire
    0.15
     entirely
    0.14
     completely
    0.14
     entirety
    0.13
    åħ¨éĥ¨
    0.12
     absolutely
    0.12
     Entire
    0.12
     whole
    0.11
     outright
    0.11
     caÅĤ
    0.11
    Activations Density 0.050%

    No Known Activations