© 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. 41194
    Prev
    Next
    INDEX
    Explanations

    references to cybersecurity and related news sources

    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
    @student
    -0.09
     Tome
    -0.08
     sóc
    -0.07
    à¤Ĺढ
    -0.07
     multiplic
    -0.07
    anean
    -0.07
    ual
    -0.07
    enguin
    -0.07
    ála
    -0.07
    .mul
    -0.06
    POSITIVE LOGITS
     article
    0.08
    .com
    0.08
    combe
    0.07
     website
    0.06
    splash
    0.06
    562
    0.06
    614
    0.06
     articles
    0.06
    website
    0.06
    odo
    0.06
    Activations Density 0.027%

    No Known Activations