© 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. 17-LLAMASCOPE-RES-131K
    11. 129792
    Prev
    Next
    INDEX
    Explanations

    content related to communication and social media management

    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
    μÏĮ
    -0.07
    rawn
    -0.07
    رÙĬع
    -0.06
     ern
    -0.06
    erchant
    -0.06
    ourke
    -0.06
    idis
    -0.06
     businessmen
    -0.06
     ur
    -0.06
    icha
    -0.06
    POSITIVE LOGITS
     content
    0.10
     communications
    0.10
    Communic
    0.09
     publication
    0.09
     Communications
    0.09
    content
    0.09
     news
    0.08
     communication
    0.08
     media
    0.08
    communications
    0.08
    Activations Density 0.020%

    No Known Activations