© 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. 89864
    Prev
    Next
    INDEX
    Explanations

    references to adult-oriented themes in comics

    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
    ÄĻk
    -0.07
    çĶļ
    -0.07
    ÑĨÑİ
    -0.07
    ãĥ³ãĥĸ
    -0.06
    ç©į
    -0.06
    æIJŀ
    -0.06
     Bund
    -0.06
     å¯Į
    -0.06
     Bones
    -0.06
    極
    -0.06
    POSITIVE LOGITS
     adult
    0.28
     grown
    0.25
     adults
    0.24
    adult
    0.24
     Adult
    0.23
     mature
    0.23
    Adult
    0.23
     adulthood
    0.21
     Adults
    0.21
     maturity
    0.20
    Activations Density 0.118%

    No Known Activations