© 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. 105851
    Prev
    Next
    INDEX
    Explanations

    structured academic writing and organization in papers

    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
    ocio
    -0.07
    oram
    -0.07
    egg
    -0.07
    uars
    -0.06
    opensource
    -0.06
    olem
    -0.06
    uo
    -0.06
    uple
    -0.06
     Dunk
    -0.06
    Ìģ
    -0.06
    POSITIVE LOGITS
     organization
    0.10
     outline
    0.10
     organisation
    0.09
     Outline
    0.09
    outline
    0.09
     layout
    0.09
     Layout
    0.08
     paper
    0.08
    organization
    0.08
     structure
    0.08
    Activations Density 0.040%

    No Known Activations