© 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. 89642
    Prev
    Next
    INDEX
    Explanations

    terms associated with community engagement and collaborative efforts

    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
    ,
    -0.08
     [],
    -0.07
    -,
    -0.07
    à¥ĭà¤Ĥ,
    -0.07
    !,
    -0.07
    !!,
    -0.06
     ?,
    -0.06
    à¥ĩ,
    -0.06
    itt
    -0.06
    cheid
    -0.06
    POSITIVE LOGITS
    以åıĬ
    0.08
    ':''
    0.08
     and
    0.08
    ãĤĬãģ¨
    0.08
    LEGRO
    0.07
     dhe
    0.07
     vÃł
    0.07
    åıĬåħ¶
    0.07
    åıĬãģ³
    0.07
     obou
    0.07
    Activations Density 0.108%

    No Known Activations