© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108555
    Prev
    Next
    INDEX
    Explanations

    terms related to Title IX and discrimination policies

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     judge
    -0.06
    rok
    -0.06
     تس
    -0.06
    gia
    -0.06
    .subplots
    -0.06
    iap
    -0.06
    TAB
    -0.06
    èģĶç½ij
    -0.06
     ac
    -0.05
    atur
    -0.05
    POSITIVE LOGITS
     Discrim
    0.08
     discrimination
    0.08
     Equal
    0.08
     equal
    0.08
    equal
    0.07
     Feder
    0.07
     discriminate
    0.07
     EQUAL
    0.07
    Equal
    0.07
     discrim
    0.07
    Activations Density 0.008%

    No Known Activations