© 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. 93790
    Prev
    Next
    INDEX
    Explanations

    the presence of news reporting and editorial commentary language

    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
    amera
    -0.07
    Ñĩив
    -0.07
    ênh
    -0.07
    олÑĮно
    -0.06
    orage
    -0.06
    implify
    -0.06
    azz
    -0.06
     ret
    -0.06
    udge
    -0.06
    ippet
    -0.06
    POSITIVE LOGITS
     NPR
    0.08
     listeners
    0.08
    Listeners
    0.08
    Listener
    0.07
     listener
    0.07
     listen
    0.07
     baise
    0.07
    listen
    0.07
    listeners
    0.07
     listens
    0.06
    Activations Density 0.003%

    No Known Activations