© 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. 42644
    Prev
    Next
    INDEX
    Explanations

    themes of righteousness and struggle against adversity

    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
    å¹
    -0.08
    erable
    -0.08
    otland
    -0.07
    geois
    -0.07
    uktur
    -0.07
    soft
    -0.07
    ambi
    -0.07
     ÑĥлÑĭб
    -0.07
    adÃŃ
    -0.07
     nebu
    -0.07
    POSITIVE LOGITS
     power
    0.09
     violent
    0.08
     mascul
    0.08
     masculine
    0.08
     hard
    0.08
     muscular
    0.08
     strong
    0.08
     force
    0.08
     rough
    0.08
     martial
    0.08
    Activations Density 0.171%

    No Known Activations