© 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. 108941
    Prev
    Next
    INDEX
    Explanations

    HTML elements and links in web content

    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
    aler
    -0.07
    anic
    -0.07
    Æ°ng
    -0.06
     apprec
    -0.06
    idd
    -0.06
    jr
    -0.05
     refr
    -0.05
    ctions
    -0.05
     haz
    -0.05
     subt
    -0.05
    POSITIVE LOGITS
    inen
    0.09
    ãĥ³ãĥIJ
    0.08
    mbH
    0.08
    опÑĢоÑģ
    0.07
    .air
    0.07
    Cre
    0.07
     POSSIBILITY
    0.07
    hashCode
    0.07
    è±Ĩ
    0.07
    деÑĢж
    0.07
    Activations Density 0.001%

    No Known Activations