© 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. 80654
    Prev
    Next
    INDEX
    Explanations

    the presence of stereotypes and myths, particularly concerning societal beliefs

    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
     Minor
    -0.06
    odable
    -0.06
    Ĩµ
    -0.06
    ết
    -0.06
    ænd
    -0.06
    gom
    -0.06
    igs
    -0.06
    uid
    -0.06
    unca
    -0.06
    olla
    -0.05
    POSITIVE LOGITS
     perception
    0.11
     perceptions
    0.11
     myths
    0.10
     stereotype
    0.10
     myth
    0.10
     Myth
    0.10
     Perception
    0.09
    以为
    0.09
     stereotypes
    0.09
     notion
    0.09
    Activations Density 0.080%

    No Known Activations