© 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. 17-LLAMASCOPE-RES-131K
    11. 26849
    Prev
    Next
    INDEX
    Explanations

    social media engagement and viewer-related queries or comments

    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
     Kara
    -0.06
    arity
    -0.06
    ta
    -0.06
    lop
    -0.06
     Gilbert
    -0.06
     Hire
    -0.06
    .kr
    -0.06
    ãĤ¿
    -0.06
    uby
    -0.05
     exhausted
    -0.05
    POSITIVE LOGITS
    issan
    0.07
    ADOW
    0.07
    latlong
    0.07
    avÄĽ
    0.06
    -validator
    0.06
     ActiveForm
    0.06
    yll
    0.06
    OOT
    0.06
    zyst
    0.06
    iom
    0.06
    Activations Density 0.002%

    No Known Activations