© 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. 121612
    Prev
    Next
    INDEX
    Explanations

    references to multimedia content and online interaction

    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
    Ñĭвал
    -0.06
     Phonetic
    -0.06
    issing
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    onen
    -0.06
    oplevel
    -0.06
     Accent
    -0.06
     viewers
    -0.06
     NOTIFY
    -0.06
     Whitney
    -0.06
    POSITIVE LOGITS
     text
    0.08
    ASC
    0.07
     video
    0.07
    video
    0.07
    ãĥĨãĥ«
    0.07
     photos
    0.07
    photos
    0.06
     textu
    0.06
     audio
    0.06
    text
    0.06
    Activations Density 0.025%

    No Known Activations