© 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 EvalsExportsinterp-engineNEWAPI 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. 104741
    Prev
    Next
    INDEX
    Explanations

    elements related to academic citations and references

    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
    oten
    -0.08
    ared
    -0.07
     bö
    -0.06
     bullet
    -0.06
     mans
    -0.06
    á»Ļi
    -0.06
    Tick
    -0.06
     vigil
    -0.06
    lich
    -0.06
    Adam
    -0.06
    POSITIVE LOGITS
    elts
    0.08
     Copyright
    0.08
     COPYRIGHT
    0.07
    æĬ¼
    0.07
    anner
    0.07
     copyright
    0.07
    inar
    0.06
    inf
    0.06
    irting
    0.06
    iado
    0.06
    Activations Density 0.006%

    No Known Activations