© 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. 5791
    Prev
    Next
    INDEX
    Explanations

    words that imply suggestion or indication

    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
    âĢij
    -0.06
    hv
    -0.06
     Dyn
    -0.06
    ochen
    -0.06
    thon
    -0.06
    -/
    -0.05
     Dra
    -0.05
    ä»
    -0.05
    _Version
    -0.05
    âĢIJ
    -0.05
    POSITIVE LOGITS
    urator
    0.08
    cura
    0.07
    quired
    0.07
    dbuf
    0.07
    Longrightarrow
    0.07
    urer
    0.07
    ContentLoaded
    0.07
    erm
    0.07
     Manufact
    0.07
    bable
    0.06
    Activations Density 0.002%

    No Known Activations