© 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. 9-LLAMASCOPE-RES-131K
    11. 97067
    Prev
    Next
    INDEX
    Explanations

    instances of content sharing and social media interactions

    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
    LAN
    -0.06
    lan
    -0.06
    GetMethod
    -0.06
    inan
    -0.06
    iks
    -0.06
    asaki
    -0.06
    lene
    -0.06
    cult
    -0.06
    ÑĨен
    -0.05
    nist
    -0.05
    POSITIVE LOGITS
    otto
    0.07
    aption
    0.06
    ä¿
    0.06
    аÑĤо
    0.06
    íĨµìĭł
    0.06
    izza
    0.06
     Candid
    0.06
    aira
    0.06
    orden
    0.06
    Ú©Ø´
    0.06
    Activations Density 0.001%

    No Known Activations