© 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. 116564
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or hypothetical scenarios

    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
    質
    -0.07
    ä¹ħ
    -0.07
     Weber
    -0.06
    avit
    -0.06
    ere
    -0.06
    joint
    -0.06
    vik
    -0.05
    ière
    -0.05
    marsh
    -0.05
     Ay
    -0.05
    POSITIVE LOGITS
    ymb
    0.08
    acific
    0.08
     alone
    0.07
    LES
    0.07
     weren
    0.07
    ä¸įè¿ĩ
    0.07
     insufficient
    0.07
     foregoing
    0.07
    å¤Ł
    0.07
     chÆ°a
    0.06
    Activations Density 0.005%

    No Known Activations