© 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. 15-LLAMASCOPE-RES-131K
    11. 61380
    Prev
    Next
    INDEX
    Explanations

    references to government transparency and information accessibility processes

    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
    SelectionMode
    -0.05
     Cres
    -0.05
     Uncategorized
    -0.05
    007
    -0.05
     scouting
    -0.05
     prof
    -0.05
     prot
    -0.05
     guided
    -0.05
    eres
    -0.05
     sad
    -0.05
    POSITIVE LOGITS
     public
    0.09
     transparency
    0.09
     púb
    0.09
    bsite
    0.09
    -public
    0.09
     publicly
    0.08
     público
    0.08
     pública
    0.08
    .public
    0.08
    fila
    0.08
    Activations Density 0.015%

    No Known Activations