© 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. 17-LLAMASCOPE-RES-131K
    11. 105719
    Prev
    Next
    INDEX
    Explanations

    guidelines and precautions for children's safety during Halloween activities

    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
     Fil
    -0.07
    宣
    -0.07
     Cage
    -0.07
    ÅĻich
    -0.07
    iferay
    -0.07
     Fell
    -0.06
    ARRIER
    -0.06
     majors
    -0.06
    /aws
    -0.06
    aginator
    -0.06
    POSITIVE LOGITS
     trick
    0.07
     Halloween
    0.07
     dressing
    0.06
     polit
    0.06
     costumes
    0.06
    _UNS
    0.06
    ç³ĸ
    0.06
     Barker
    0.06
     Sugar
    0.06
     Trick
    0.06
    Activations Density 0.061%

    No Known Activations