© 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. 9-LLAMASCOPE-RES-131K
    11. 95283
    Prev
    Next
    INDEX
    Explanations

    terminology related to mailing and shipping processes

    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
    illa
    -0.06
    263
    -0.06
     minim
    -0.06
     AS
    -0.06
    ury
    -0.06
     mod
    -0.06
    д
    -0.06
    ollo
    -0.06
    173
    -0.06
     gn
    -0.06
    POSITIVE LOGITS
    omit
    0.08
    onden
    0.08
    .useState
    0.08
    ourmet
    0.08
    afia
    0.08
    itant
    0.07
    antium
    0.07
    /browse
    0.07
    gua
    0.07
    oron
    0.07
    Activations Density 0.004%

    No Known Activations