© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89201
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate societal structures and power dynamics

    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
    Fcn
    -0.08
    mÃŃ
    -0.08
    ennie
    -0.08
    ataire
    -0.07
    plits
    -0.07
    IIIK
    -0.07
    ãĤŃãĥ³ãĤ°
    -0.07
    usch
    -0.07
    uso
    -0.07
     overposting
    -0.07
    POSITIVE LOGITS
     Drag
    0.06
     establishments
    0.06
    772
    0.06
     Rug
    0.05
    ENDED
    0.05
     drowned
    0.05
     drag
    0.05
     slo
    0.05
     Bark
    0.05
    ecimal
    0.05
    Activations Density 0.000%

    No Known Activations