© 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. 17-LLAMASCOPE-RES-131K
    11. 126495
    Prev
    Next
    INDEX
    Explanations

    phrases indicating criticism or concern about social issues and injustices

    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
    Verdana
    -0.08
    ILA
    -0.07
    .appspot
    -0.07
    ouns
    -0.07
    μÏĨ
    -0.07
    acter
    -0.07
    ISCO
    -0.07
    ila
    -0.07
    prung
    -0.06
    _initializer
    -0.06
    POSITIVE LOGITS
    å¦ĤæѤ
    0.09
    ç«Ł
    0.07
     such
    0.07
     regress
    0.07
     so
    0.07
    akit
    0.07
     while
    0.06
     modern
    0.06
     basic
    0.06
     grown
    0.06
    Activations Density 0.024%

    No Known Activations