© 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 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. 87914
    Prev
    Next
    INDEX
    Explanations

    discourse involving societal and political conflicts, particularly around justice and representation

    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
    avorites
    -0.06
    aland
    -0.06
     ASTM
    -0.06
    elli
    -0.06
    ernal
    -0.06
    inya
    -0.06
    ostat
    -0.06
    isable
    -0.05
    ÑĪе
    -0.05
    opaque
    -0.05
    POSITIVE LOGITS
    ivy
    0.06
     bát
    0.06
    gba
    0.06
    ation
    0.06
     retrofit
    0.06
    mlin
    0.06
     fuss
    0.06
    mdi
    0.06
    .MEDIA
    0.06
    Ø´ÙĨ
    0.06
    Activations Density 0.008%

    No Known Activations