© 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. 76525
    Prev
    Next
    INDEX
    Explanations

    references to cultural and societal critiques

    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
    -0.07
    инок
    -0.06
    dsp
    -0.06
    udder
    -0.06
    èĸ
    -0.06
    .GetObject
    -0.06
    aben
    -0.06
    DP
    -0.06
     Turns
    -0.06
    CompleteListener
    -0.06
    POSITIVE LOGITS
    iento
    0.07
    ิà¸Ī
    0.07
    hetto
    0.07
    emailer
    0.07
    ewhat
    0.06
    oose
    0.06
    ÑģÑĤан
    0.06
     Bald
    0.06
    itis
    0.06
    san
    0.06
    Activations Density 0.175%

    No Known Activations