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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 74722
    Prev
    Next
    INDEX
    Explanations

    criticisms of opinions or actions, particularly in social or political contexts

    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
    fault
    -0.07
    askell
    -0.07
    ابع
    -0.07
     süre
    -0.07
    lfw
    -0.07
    acula
    -0.07
    umbs
    -0.06
    aws
    -0.06
    createForm
    -0.06
    леменÑĤ
    -0.06
    POSITIVE LOGITS
     stop
    0.07
    -stop
    0.07
    lej
    0.06
    ichel
    0.06
     real
    0.06
    ippi
    0.06
     Angry
    0.06
    stop
    0.06
     Stop
    0.06
     remed
    0.06
    Activations Density 0.037%

    No Known Activations