© 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. 60026
    Prev
    Next
    INDEX
    Explanations

    references to rules, requirements, and classifications within various contexts

    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
     именно
    -0.06
     HQ
    -0.06
     thereby
    -0.06
     ping
    -0.06
     právÄĽ
    -0.06
    now
    -0.06
     пÑĢежде
    -0.06
    ÅĤy
    -0.05
    und
    -0.05
    irler
    -0.05
    POSITIVE LOGITS
    exceptions
    0.08
     exceptions
    0.08
     similarly
    0.08
     exception
    0.08
     generally
    0.08
    åīĩ
    0.08
    ubbo
    0.07
    åĪĻ
    0.07
    .MixedReality
    0.07
    rech
    0.07
    Activations Density 0.052%

    No Known Activations