© 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. 15623
    Prev
    Next
    INDEX
    Explanations

    references to guidance and instructions

    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
    LOB
    -0.07
    hower
    -0.06
     –
    -0.06
     Admin
    -0.06
     admin
    -0.06
     -
    -0.06
    ADMIN
    -0.06
    567
    -0.06
     fab
    -0.06
     admins
    -0.06
    POSITIVE LOGITS
    ivec
    0.08
    .DataTable
    0.07
    hopefully
    0.07
     ÑĤÑĢен
    0.07
    ableObject
    0.07
     Kraj
    0.07
     aray
    0.07
     ofType
    0.07
     withd
    0.07
    ainless
    0.07
    Activations Density 0.000%

    No Known Activations