© 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. 93458
    Prev
    Next
    INDEX
    Explanations

    themes related to branding and identity changes

    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
    undos
    -0.06
    IfExists
    -0.06
    ÙĦÙĬÙĦ
    -0.06
    mos
    -0.06
     deflate
    -0.06
    stitutions
    -0.06
    <num
    -0.06
    rote
    -0.06
    orks
    -0.06
    ÏĢÏīÏĤ
    -0.06
    POSITIVE LOGITS
     brand
    0.08
     identity
    0.08
     change
    0.07
    åĵģçīĮ
    0.07
    identity
    0.07
     Identity
    0.07
    brand
    0.06
     company
    0.06
     branding
    0.06
     brands
    0.06
    Activations Density 0.018%

    No Known Activations