© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94079
    Prev
    Next
    INDEX
    Explanations

    content related to website usage and cookie policies

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ucken
    -0.07
    berger
    -0.07
    μÏĨ
    -0.07
    Abstract
    -0.07
    微软éĽħé»ij
    -0.06
    룬리
    -0.06
    ¦Ĥ
    -0.06
    reate
    -0.06
    EMU
    -0.06
    emu
    -0.06
    POSITIVE LOGITS
    unkt
    0.06
    olars
    0.06
    å°ıå§IJ
    0.06
     nÄĥ
    0.06
    aman
    0.06
    ulse
    0.05
    719
    0.05
    .robot
    0.05
    å³
    0.05
    edor
    0.05
    Activations Density 0.004%

    No Known Activations