© 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. 77892
    Prev
    Next
    INDEX
    Explanations

    terms related to business and corporate contexts

    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
    lech
    -0.07
    stras
    -0.06
    retch
    -0.06
     cancelButtonTitle
    -0.06
    udio
    -0.06
    سÙĦ
    -0.06
    akash
    -0.06
    ãģŀ
    -0.06
    åħ¬å¼Ģ
    -0.06
    iosa
    -0.06
    POSITIVE LOGITS
    -wide
    0.08
    wide
    0.07
     wide
    0.07
    trand
    0.07
    anal
    0.06
    odash
    0.06
    arus
    0.06
    arden
    0.06
    /world
    0.06
    ÏĥÏĥα
    0.06
    Activations Density 0.006%

    No Known Activations