© 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. 77152
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to writing and content creation strategies

    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
     discount
    -0.06
    ari
    -0.06
    ork
    -0.05
    isos
    -0.05
    lex
    -0.05
    cap
    -0.05
     discounted
    -0.05
     administration
    -0.05
     Schwartz
    -0.05
     mobility
    -0.05
    POSITIVE LOGITS
     content
    0.09
     Content
    0.09
     CONTENT
    0.08
     contenu
    0.07
    .content
    0.07
    åĨħ容
    0.07
    _Content
    0.07
    à¹Ģà¸Ļ
    0.07
    ,content
    0.07
    koli
    0.07
    Activations Density 0.055%

    No Known Activations