© 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. 54495
    Prev
    Next
    INDEX
    Explanations

    specific locations or contexts related to a variety of issues

    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
     sonucunda
    -0.08
    obraz
    -0.07
    oader
    -0.07
     вÑģем
    -0.07
    ilden
    -0.07
    živ
    -0.07
    .Txt
    -0.07
    ormsg
    -0.07
     góc
    -0.07
    بÙĪاسطة
    -0.07
    POSITIVE LOGITS
     there
    0.10
     where
    0.09
    ver
    0.07
     it
    0.07
     such
    0.06
    -local
    0.06
    where
    0.06
     either
    0.06
     they
    0.06
     conditions
    0.06
    Activations Density 0.023%

    No Known Activations