© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 125698
    Prev
    Next
    INDEX
    Explanations

    research studies and their results related to health and lifestyle

    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
    agan
    -0.07
    amic
    -0.06
    rib
    -0.06
    jian
    -0.06
     ÑĢеб
    -0.06
    ÑĥлÑİ
    -0.06
    ema
    -0.06
    á»ħ
    -0.06
    eyn
    -0.06
     blessing
    -0.05
    POSITIVE LOGITS
     limitations
    0.10
     limitation
    0.10
    limitations
    0.09
     limited
    0.09
     Limit
    0.09
     cave
    0.08
     Cave
    0.08
    limited
    0.08
    éĻIJ
    0.08
     study
    0.08
    Activations Density 0.025%

    No Known Activations