© 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. 104127
    Prev
    Next
    INDEX
    Explanations

    references to data analysis and assessment of real-world implications

    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
    mtree
    -0.07
    itta
    -0.07
    ï¼Ń
    -0.07
    stoup
    -0.07
     undermin
    -0.06
     cigaret
    -0.06
     dün
    -0.06
     Erotik
    -0.06
    è¼Ŀ
    -0.06
    (çģ«
    -0.06
    POSITIVE LOGITS
     reality
    0.14
     actual
    0.13
     actually
    0.12
     true
    0.11
    actual
    0.11
    Reality
    0.10
     Reality
    0.10
     realidad
    0.09
    true
    0.09
     real
    0.09
    Activations Density 0.031%

    No Known Activations