© 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. 119951
    Prev
    Next
    INDEX
    Explanations

    references to historical significance or symbolism

    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
    ocket
    -0.09
    ãĥĬãĥ«
    -0.08
    gren
    -0.07
    .weixin
    -0.07
    á»±
    -0.07
    ubic
    -0.07
    мÑĸнÑĸ
    -0.07
    orney
    -0.07
    òng
    -0.07
    ëĭ¹
    -0.07
    POSITIVE LOGITS
     decades
    0.11
     centuries
    0.10
     century
    0.09
     века
    0.07
     generations
    0.07
    jak
    0.07
     Cent
    0.07
     years
    0.06
     sore
    0.06
     long
    0.06
    Activations Density 0.047%

    No Known Activations