© 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. 17-LLAMASCOPE-RES-131K
    11. 74977
    Prev
    Next
    INDEX
    Explanations

    elements related to persuasive techniques and rhetorical concepts

    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
    itten
    -0.07
    -enter
    -0.07
    inkle
    -0.07
    anz
    -0.06
    lay
    -0.06
    romosome
    -0.06
    phabet
    -0.06
    ovie
    -0.06
     Knot
    -0.06
     Vocabulary
    -0.06
    POSITIVE LOGITS
     technique
    0.07
    utzer
    0.07
    kke
    0.06
    ÙĦÙĪب
    0.06
     strategy
    0.06
    UNET
    0.06
     вÑĭдел
    0.06
     Kong
    0.06
    strategy
    0.06
    arrant
    0.06
    Activations Density 0.007%

    No Known Activations