© 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. 63219
    Prev
    Next
    INDEX
    Explanations

    discussions about media formats and their availability

    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
    arel
    -0.06
     onBind
    -0.06
    в
    -0.06
    oral
    -0.06
    IDA
    -0.06
    uthor
    -0.05
    Backup
    -0.05
    ìĽĥ
    -0.05
     refl
    -0.05
     adaptation
    -0.05
    POSITIVE LOGITS
     format
    0.07
     CONTENT
    0.07
    оÑĢоÑĤ
    0.07
    CONTENT
    0.07
     verz
    0.07
    (contents
    0.07
    Contents
    0.07
    à¸Ħรà¸ļ
    0.07
    format
    0.07
    æĶ¶å½ķ
    0.07
    Activations Density 0.007%

    No Known Activations