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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41211
    Prev
    Next
    INDEX
    Explanations

    concepts related to social inequality and discrimination against marginalized groups

    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
    acos
    -0.07
    اÙĦÙĩ
    -0.06
     offsetof
    -0.06
    wie
    -0.06
     TypeName
    -0.06
    quiv
    -0.06
    .lambda
    -0.06
    allen
    -0.06
    à¤Ĥर
    -0.06
     atd
    -0.06
    POSITIVE LOGITS
    yms
    0.08
    umm
    0.07
    yet
    0.07
     yet
    0.07
    erb
    0.06
    ubat
    0.06
    ynn
    0.06
    emma
    0.06
    Reviewed
    0.06
     daher
    0.06
    Activations Density 0.046%

    No Known Activations